Upload 82 files

LLM-Detector-V7-11w/src/api_demo.py

@@ -0,0 +1,15 @@
+import os
+import uvicorn
+
+from llmtuner import ChatModel, create_app
+
+
+def main():
+    chat_model = ChatModel()
+    app = create_app(chat_model)
+    print("Visit http://localhost:{}/docs for API document.".format(os.environ.get("API_PORT", 8000)))
+    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("API_PORT", 8000)), workers=1)
+
+
+if __name__ == "__main__":
+    main()

LLM-Detector-V7-11w/src/cli_demo.py

@@ -0,0 +1,47 @@
+from llmtuner import ChatModel
+from llmtuner.extras.misc import torch_gc
+
+try:
+    import platform
+    if platform.system() != "Windows":
+        import readline
+except ImportError:
+    print("Install `readline` for a better experience.")
+
+
+def main():
+    chat_model = ChatModel()
+    history = []
+    print("Welcome to the CLI application, use `clear` to remove the history, use `exit` to exit the application.")
+
+    while True:
+        try:
+            query = input("\nUser: ")
+        except UnicodeDecodeError:
+            print("Detected decoding error at the inputs, please set the terminal encoding to utf-8.")
+            continue
+        except Exception:
+            raise
+
+        if query.strip() == "exit":
+            break
+
+        if query.strip() == "clear":
+            history = []
+            torch_gc()
+            print("History has been removed.")
+            continue
+
+        print("Assistant: ", end="", flush=True)
+
+        response = ""
+        for new_text in chat_model.stream_chat(query, history):
+            print(new_text, end="", flush=True)
+            response += new_text
+        print()
+
+        history = history + [(query, response)]
+
+
+if __name__ == "__main__":
+    main()

LLM-Detector-V7-11w/src/evaluate.py

@@ -0,0 +1,10 @@
+from llmtuner import Evaluator
+
+
+def main():
+    evaluator = Evaluator()
+    evaluator.eval()
+
+
+if __name__ == "__main__":
+    main()

LLM-Detector-V7-11w/src/export_model.py

@@ -0,0 +1,9 @@
+from llmtuner import export_model
+
+
+def main():
+    export_model()
+
+
+if __name__ == "__main__":
+    main()

LLM-Detector-V7-11w/src/llmtuner/__init__.py

@@ -0,0 +1,10 @@
+# Level: api, webui > chat, eval, train > data, model > extras, hparams
+
+from llmtuner.api import create_app
+from llmtuner.chat import ChatModel
+from llmtuner.eval import Evaluator
+from llmtuner.train import export_model, run_exp
+from llmtuner.webui import create_ui, create_web_demo
+
+
+__version__ = "0.4.0"

LLM-Detector-V7-11w/src/llmtuner/api/__init__.py

@@ -0,0 +1 @@
+from llmtuner.api.app import create_app

LLM-Detector-V7-11w/src/llmtuner/api/app.py

@@ -0,0 +1,195 @@
+import os
+import json
+import asyncio
+from typing import List, Tuple
+from pydantic import BaseModel
+from contextlib import asynccontextmanager
+
+from llmtuner.api.protocol import (
+    Role,
+    Finish,
+    ModelCard,
+    ModelList,
+    ChatMessage,
+    DeltaMessage,
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ChatCompletionStreamResponse,
+    ChatCompletionResponseChoice,
+    ChatCompletionResponseStreamChoice,
+    ChatCompletionResponseUsage,
+    ScoreEvaluationRequest,
+    ScoreEvaluationResponse
+)
+from llmtuner.chat import ChatModel
+from llmtuner.extras.misc import torch_gc
+from llmtuner.extras.packages import (
+    is_fastapi_availble, is_starlette_available, is_uvicorn_available
+)
+
+
+if is_fastapi_availble():
+    from fastapi import FastAPI, HTTPException, status
+    from fastapi.middleware.cors import CORSMiddleware
+
+
+if is_starlette_available():
+    from sse_starlette import EventSourceResponse
+
+
+if is_uvicorn_available():
+    import uvicorn
+
+
+@asynccontextmanager
+async def lifespan(app: "FastAPI"): # collects GPU memory
+    yield
+    torch_gc()
+
+
+def to_json(data: BaseModel) -> str:
+    try: # pydantic v2
+        return json.dumps(data.model_dump(exclude_unset=True), ensure_ascii=False)
+    except: # pydantic v1
+        return data.json(exclude_unset=True, ensure_ascii=False)
+
+
+def create_app(chat_model: "ChatModel") -> "FastAPI":
+    app = FastAPI(lifespan=lifespan)
+
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=["*"],
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+    semaphore = asyncio.Semaphore(int(os.environ.get("MAX_CONCURRENT", 1)))
+
+    @app.get("/v1/models", response_model=ModelList)
+    async def list_models():
+        model_card = ModelCard(id="gpt-3.5-turbo")
+        return ModelList(data=[model_card])
+
+    @app.post("/v1/chat/completions", response_model=ChatCompletionResponse, status_code=status.HTTP_200_OK)
+    async def create_chat_completion(request: ChatCompletionRequest):
+        if not chat_model.can_generate:
+            raise HTTPException(status_code=status.HTTP_405_METHOD_NOT_ALLOWED, detail="Not allowed")
+
+        if len(request.messages) == 0 or request.messages[-1].role != Role.USER:
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid request")
+
+        query = request.messages[-1].content
+        prev_messages = request.messages[:-1]
+        if len(prev_messages) and prev_messages[0].role == Role.SYSTEM:
+            system = prev_messages.pop(0).content
+        else:
+            system = None
+
+        history = []
+        if len(prev_messages) % 2 == 0:
+            for i in range(0, len(prev_messages), 2):
+                if prev_messages[i].role == Role.USER and prev_messages[i+1].role == Role.ASSISTANT:
+                    history.append([prev_messages[i].content, prev_messages[i+1].content])
+                else:
+                    raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Only supports u/a/u/a/u...")
+        else:
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Only supports u/a/u/a/u...")
+
+        async with semaphore:
+            loop = asyncio.get_running_loop()
+            return await loop.run_in_executor(None, chat_completion, query, history, system, request)
+
+    def chat_completion(query: str, history: List[Tuple[str, str]], system: str, request: ChatCompletionRequest):
+        if request.stream:
+            generate = stream_chat_completion(query, history, system, request)
+            return EventSourceResponse(generate, media_type="text/event-stream")
+
+        responses = chat_model.chat(
+            query, history, system,
+            do_sample=request.do_sample,
+            temperature=request.temperature,
+            top_p=request.top_p,
+            max_new_tokens=request.max_tokens,
+            num_return_sequences=request.n
+        )
+
+        prompt_length, response_length = 0, 0
+        choices = []
+        for i, response in enumerate(responses):
+            choices.append(ChatCompletionResponseChoice(
+                index=i,
+                message=ChatMessage(role=Role.ASSISTANT, content=response.response_text),
+                finish_reason=Finish.STOP if response.finish_reason == "stop" else Finish.LENGTH
+            ))
+            prompt_length = response.prompt_length
+            response_length += response.response_length
+
+        usage = ChatCompletionResponseUsage(
+            prompt_tokens=prompt_length,
+            completion_tokens=response_length,
+            total_tokens=prompt_length+response_length
+        )
+
+        return ChatCompletionResponse(model=request.model, choices=choices, usage=usage)
+
+    def stream_chat_completion(query: str, history: List[Tuple[str, str]], system: str, request: ChatCompletionRequest):
+        choice_data = ChatCompletionResponseStreamChoice(
+            index=0,
+            delta=DeltaMessage(role=Role.ASSISTANT, content=""),
+            finish_reason=None
+        )
+        chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
+        yield to_json(chunk)
+
+        for new_text in chat_model.stream_chat(
+            query, history, system,
+            do_sample=request.do_sample,
+            temperature=request.temperature,
+            top_p=request.top_p,
+            max_new_tokens=request.max_tokens
+        ):
+            if len(new_text) == 0:
+                continue
+
+            choice_data = ChatCompletionResponseStreamChoice(
+                index=0,
+                delta=DeltaMessage(content=new_text),
+                finish_reason=None
+            )
+            chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
+            yield to_json(chunk)
+
+        choice_data = ChatCompletionResponseStreamChoice(
+            index=0,
+            delta=DeltaMessage(),
+            finish_reason=Finish.STOP
+        )
+        chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
+        yield to_json(chunk)
+        yield "[DONE]"
+
+    @app.post("/v1/score/evaluation", response_model=ScoreEvaluationResponse, status_code=status.HTTP_200_OK)
+    async def create_score_evaluation(request: ScoreEvaluationRequest):
+        if chat_model.can_generate:
+            raise HTTPException(status_code=status.HTTP_405_METHOD_NOT_ALLOWED, detail="Not allowed")
+
+        if len(request.messages) == 0:
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid request")
+
+        async with semaphore:
+            loop = asyncio.get_running_loop()
+            return await loop.run_in_executor(None, get_score, request)
+
+    def get_score(request: ScoreEvaluationRequest):
+        scores = chat_model.get_scores(request.messages, max_length=request.max_length)
+        return ScoreEvaluationResponse(model=request.model, scores=scores)
+
+    return app
+
+
+if __name__ == "__main__":
+    chat_model = ChatModel()
+    app = create_app(chat_model)
+    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("API_PORT", 8000)), workers=1)

LLM-Detector-V7-11w/src/llmtuner/api/protocol.py

@@ -0,0 +1,96 @@
+import time
+from enum import Enum
+from pydantic import BaseModel, Field
+from typing import List, Optional
+
+
+class Role(str, Enum):
+    USER = "user"
+    ASSISTANT = "assistant"
+    SYSTEM = "system"
+
+
+class Finish(str, Enum):
+    STOP = "stop"
+    LENGTH = "length"
+
+
+class ModelCard(BaseModel):
+    id: str
+    object: Optional[str] = "model"
+    created: Optional[int] = Field(default_factory=lambda: int(time.time()))
+    owned_by: Optional[str] = "owner"
+
+
+class ModelList(BaseModel):
+    object: Optional[str] = "list"
+    data: Optional[List[ModelCard]] = []
+
+
+class ChatMessage(BaseModel):
+    role: Role
+    content: str
+
+
+class DeltaMessage(BaseModel):
+    role: Optional[Role] = None
+    content: Optional[str] = None
+
+
+class ChatCompletionRequest(BaseModel):
+    model: str
+    messages: List[ChatMessage]
+    do_sample: Optional[bool] = True
+    temperature: Optional[float] = None
+    top_p: Optional[float] = None
+    n: Optional[int] = 1
+    max_tokens: Optional[int] = None
+    stream: Optional[bool] = False
+
+
+class ChatCompletionResponseChoice(BaseModel):
+    index: int
+    message: ChatMessage
+    finish_reason: Finish
+
+
+class ChatCompletionResponseStreamChoice(BaseModel):
+    index: int
+    delta: DeltaMessage
+    finish_reason: Optional[Finish] = None
+
+
+class ChatCompletionResponseUsage(BaseModel):
+    prompt_tokens: int
+    completion_tokens: int
+    total_tokens: int
+
+
+class ChatCompletionResponse(BaseModel):
+    id: Optional[str] = "chatcmpl-default"
+    object: Optional[str] = "chat.completion"
+    created: Optional[int] = Field(default_factory=lambda: int(time.time()))
+    model: str
+    choices: List[ChatCompletionResponseChoice]
+    usage: ChatCompletionResponseUsage
+
+
+class ChatCompletionStreamResponse(BaseModel):
+    id: Optional[str] = "chatcmpl-default"
+    object: Optional[str] = "chat.completion.chunk"
+    created: Optional[int] = Field(default_factory=lambda: int(time.time()))
+    model: str
+    choices: List[ChatCompletionResponseStreamChoice]
+
+
+class ScoreEvaluationRequest(BaseModel):
+    model: str
+    messages: List[str]
+    max_length: Optional[int] = None
+
+
+class ScoreEvaluationResponse(BaseModel):
+    id: Optional[str] = "scoreeval-default"
+    object: Optional[str] = "score.evaluation"
+    model: str
+    scores: List[float]

LLM-Detector-V7-11w/src/llmtuner/chat/__init__.py

@@ -0,0 +1 @@
+from llmtuner.chat.chat_model import ChatModel

LLM-Detector-V7-11w/src/llmtuner/chat/chat_model.py

@@ -0,0 +1,171 @@
+import torch
+import tiktoken
+from dataclasses import dataclass
+from typing import Any, Dict, Generator, List, Literal, Optional, Tuple
+from threading import Thread
+from transformers import GenerationConfig, TextIteratorStreamer
+
+from llmtuner.data.template import get_template_and_fix_tokenizer
+from llmtuner.extras.misc import get_logits_processor
+from llmtuner.model import dispatch_model, get_infer_args, load_model_and_tokenizer
+
+
+@dataclass
+class Response:
+
+    response_text: str
+    response_length: int
+    prompt_length: int
+    finish_reason: Literal["stop", "length"]
+
+
+class ChatModel:
+
+    def __init__(self, args: Optional[Dict[str, Any]] = None) -> None:
+        model_args, data_args, finetuning_args, self.generating_args = get_infer_args(args)
+        self.can_generate = (finetuning_args.stage == "sft")
+        self.model, self.tokenizer = load_model_and_tokenizer(
+            model_args, finetuning_args, is_trainable=False, add_valuehead=(not self.can_generate)
+        )
+        self.tokenizer.padding_side = "left" if self.can_generate else "right"
+        self.model = dispatch_model(self.model)
+        self.template = get_template_and_fix_tokenizer(data_args.template, self.tokenizer)
+
+    def _process_args(
+        self,
+        query: str,
+        history: Optional[List[Tuple[str, str]]] = None,
+        system: Optional[str] = None,
+        **input_kwargs
+    ) -> Tuple[Dict[str, Any], int]:
+        prompt, _ = self.template.encode_oneturn(
+            tokenizer=self.tokenizer, query=query, resp="", history=history, system=system
+        )
+        prompt_length = len(prompt)
+        input_ids = torch.tensor([prompt], device=self.model.device)
+
+        do_sample = input_kwargs.pop("do_sample", None)
+        temperature = input_kwargs.pop("temperature", None)
+        top_p = input_kwargs.pop("top_p", None)
+        top_k = input_kwargs.pop("top_k", None)
+        num_return_sequences = input_kwargs.pop("num_return_sequences", None)
+        repetition_penalty = input_kwargs.pop("repetition_penalty", None)
+        max_length = input_kwargs.pop("max_length", None)
+        max_new_tokens = input_kwargs.pop("max_new_tokens", None)
+
+        generating_args = self.generating_args.to_dict()
+        generating_args.update(dict(
+            do_sample=do_sample if do_sample is not None else generating_args["do_sample"],
+            temperature=temperature or generating_args["temperature"],
+            top_p=top_p or generating_args["top_p"],
+            top_k=top_k or generating_args["top_k"],
+            num_return_sequences=num_return_sequences or 1,
+            repetition_penalty=repetition_penalty or generating_args["repetition_penalty"],
+            eos_token_id=[self.tokenizer.eos_token_id] + self.tokenizer.additional_special_tokens_ids,
+            pad_token_id=self.tokenizer.pad_token_id
+        ))
+
+        if isinstance(num_return_sequences, int) and num_return_sequences > 1:
+            generating_args["do_sample"] = True
+
+        if max_length:
+            generating_args.pop("max_new_tokens", None)
+            generating_args["max_length"] = max_length
+
+        if max_new_tokens:
+            generating_args.pop("max_length", None)
+            generating_args["max_new_tokens"] = max_new_tokens
+
+        gen_kwargs = dict(
+            inputs=input_ids,
+            generation_config=GenerationConfig(**generating_args),
+            logits_processor=get_logits_processor()
+        )
+
+        return gen_kwargs, prompt_length
+
+    @torch.inference_mode()
+    def chat(
+        self,
+        query: str,
+        history: Optional[List[Tuple[str, str]]] = None,
+        system: Optional[str] = None,
+        **input_kwargs
+    ) -> List[Response]:
+        r"""
+        Args: query, history, system, **input_kwargs
+
+        Returns: [(response_text, prompt_length, response_length)] * n (default n=1)
+        """
+        gen_kwargs, prompt_length = self._process_args(query, history, system, **input_kwargs)
+        generate_output = self.model.generate(**gen_kwargs)
+        response_ids = generate_output[:, prompt_length:]
+        response = self.tokenizer.batch_decode(
+            response_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
+        )
+        results = []
+        for i in range(len(response)):
+            eos_index = (response_ids[i] == self.tokenizer.eos_token_id).nonzero()
+            response_length = (eos_index[0].item() + 1) if len(eos_index) else len(response_ids[i])
+            results.append(Response(
+                response_text=response[i],
+                response_length=response_length,
+                prompt_length=prompt_length,
+                finish_reason="stop" if len(eos_index) else "length"
+            ))
+
+        return results
+
+    @torch.inference_mode()
+    def stream_chat(
+        self,
+        query: str,
+        history: Optional[List[Tuple[str, str]]] = None,
+        system: Optional[str] = None,
+        **input_kwargs
+    ) -> Generator[str, None, None]:
+        gen_kwargs, _ = self._process_args(query, history, system, **input_kwargs)
+        streamer = TextIteratorStreamer(self.tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
+        gen_kwargs["streamer"] = streamer
+
+        thread = Thread(target=self.model.generate, kwargs=gen_kwargs)
+        thread.start()
+
+        yield from streamer
+
+    @torch.inference_mode()
+    def get_scores(
+        self,
+        batch_input: List[str],
+        **input_kwargs
+    ) -> List[float]:
+        if isinstance(getattr(self.tokenizer, "tokenizer", None), tiktoken.Encoding): # for tiktoken tokenizer (Qwen)
+            kwargs = dict(allowed_special="all")
+        else:
+            kwargs = dict(add_special_tokens=True)
+
+        max_length = input_kwargs.pop("max_length", None)
+        device = getattr(self.model.pretrained_model, "device", "cuda")
+
+        inputs = self.tokenizer(
+            batch_input,
+            padding=True,
+            truncation=True,
+            max_length=max_length or getattr(self.model.config, "max_position_embeddings", 1024),
+            return_tensors="pt",
+            **kwargs
+        ).to(device)
+
+        input_ids: torch.Tensor = inputs["input_ids"]
+        _, _, values = self.model(**inputs, output_hidden_states=True, return_dict=True)
+
+        if getattr(self.model.config, "model_type", None) == "chatglm":
+            values = torch.transpose(values, 0, 1)
+
+        scores = []
+        for i in range(input_ids.size(0)):
+            end_indexes = (input_ids[i] != self.tokenizer.pad_token_id).nonzero()
+            end_index = end_indexes[-1].item() if len(end_indexes) else 0
+            scores.append(values[i, end_index].nan_to_num().item())
+
+        return scores

LLM-Detector-V7-11w/src/llmtuner/data/__init__.py

@@ -0,0 +1,4 @@
+from llmtuner.data.loader import get_dataset
+from llmtuner.data.preprocess import preprocess_dataset
+from llmtuner.data.template import get_template_and_fix_tokenizer
+from llmtuner.data.utils import split_dataset

LLM-Detector-V7-11w/src/llmtuner/data/loader.py

@@ -0,0 +1,173 @@
+import os
+from typing import TYPE_CHECKING, Any, Dict, List, Union
+
+from datasets import concatenate_datasets, interleave_datasets, load_dataset, load_from_disk
+
+from llmtuner.data.utils import checksum
+from llmtuner.extras.constants import FILEEXT2TYPE
+from llmtuner.extras.logging import get_logger
+
+if TYPE_CHECKING:
+    from datasets import Dataset, IterableDataset
+    from llmtuner.hparams import ModelArguments, DataArguments
+
+
+logger = get_logger(__name__)
+
+
+def get_dataset(
+    model_args: "ModelArguments",
+    data_args: "DataArguments"
+) -> Union["Dataset", "IterableDataset"]:
+    max_samples = data_args.max_samples
+    all_datasets: List[Union["Dataset", "IterableDataset"]] = [] # support multiple datasets
+
+    if data_args.cache_path is not None:
+        if os.path.exists(data_args.cache_path):
+            logger.warning("Loading dataset from disk will ignore other data arguments.")
+            dataset = load_from_disk(data_args.cache_path)
+            if data_args.streaming:
+                dataset = dataset.to_iterable_dataset()
+            return dataset
+        elif data_args.streaming:
+            raise ValueError("Turn off dataset streaming to save cache files.")
+
+    for dataset_attr in data_args.dataset_list:
+        logger.info("Loading dataset {}...".format(dataset_attr))
+
+        data_path, data_name, data_dir, data_files = None, None, None, None
+        if dataset_attr.load_from in ["hf_hub", "ms_hub"]:
+            data_path = dataset_attr.dataset_name
+            data_name = dataset_attr.subset
+            data_dir = dataset_attr.folder
+        elif dataset_attr.load_from == "script":
+            data_path = os.path.join(data_args.dataset_dir, dataset_attr.dataset_name)
+            data_name = dataset_attr.subset
+        elif dataset_attr.load_from == "file":
+            data_files = []
+            local_path: str = os.path.join(data_args.dataset_dir, dataset_attr.dataset_name)
+            if os.path.isdir(local_path): # is directory
+                for file_name in os.listdir(local_path):
+                    data_files.append(os.path.join(local_path, file_name))
+                    if data_path is None:
+                        data_path = FILEEXT2TYPE.get(file_name.split(".")[-1], None)
+                    else:
+                        assert data_path == FILEEXT2TYPE.get(file_name.split(".")[-1], None), "file types are not identical."
+            elif os.path.isfile(local_path): # is file
+                data_files.append(local_path)
+                data_path = FILEEXT2TYPE.get(local_path.split(".")[-1], None)
+            else:
+                raise ValueError("File not found.")
+
+            assert data_path, "File extension must be txt, csv, json or jsonl."
+            checksum(data_files, dataset_attr.dataset_sha1)
+        else:
+            raise NotImplementedError
+
+        if dataset_attr.load_from == "ms_hub":
+            try:
+                from modelscope import MsDataset
+                from modelscope.utils.config_ds import MS_DATASETS_CACHE
+
+                cache_dir = model_args.cache_dir or MS_DATASETS_CACHE
+                dataset = MsDataset.load(
+                    dataset_name=data_path,
+                    subset_name=data_name,
+                    data_dir=data_dir,
+                    data_files=data_files,
+                    split=data_args.split,
+                    cache_dir=cache_dir,
+                    token=model_args.ms_hub_token,
+                    use_streaming=(data_args.streaming and (dataset_attr.load_from != "file"))
+                ).to_hf_dataset()
+            except ImportError:
+                raise ImportError("Please install modelscope via `pip install modelscope -U`")
+        else:
+            dataset = load_dataset(
+                path=data_path,
+                name=data_name,
+                data_dir=data_dir,
+                data_files=data_files,
+                split=data_args.split,
+                cache_dir=model_args.cache_dir,
+                token=model_args.hf_hub_token,
+                streaming=(data_args.streaming and (dataset_attr.load_from != "file"))
+            )
+
+        if data_args.streaming and (dataset_attr.load_from == "file"): # faster than specifying streaming=True
+            dataset = dataset.to_iterable_dataset() # TODO: add num shards parameter
+
+        if max_samples is not None: # truncate dataset
+            dataset = dataset.select(range(min(len(dataset), max_samples)))
+
+        def convert_format(examples: Dict[str, List[Any]]) -> Dict[str, List[Any]]:
+            # convert dataset from sharegpt format to alpaca format
+            outputs = {"prompt": [], "query": [], "response": [], "history": [], "system": []}
+            for i, msg_list in enumerate(examples[dataset_attr.messages]):
+                msg_list = msg_list[:len(msg_list) // 2 * 2] # should be multiples of 2
+                if len(msg_list) == 0:
+                    continue
+
+                msg_pairs = []
+                user_role, assistant_role = None, None
+                for idx in range(0, len(msg_list), 2):
+                    if user_role is None and assistant_role is None:
+                        user_role = msg_list[idx][dataset_attr.role]
+                        assistant_role = msg_list[idx + 1][dataset_attr.role]
+                    else:
+                        if (
+                            msg_list[idx][dataset_attr.role] != user_role
+                            or msg_list[idx+1][dataset_attr.role] != assistant_role
+                        ):
+                            raise ValueError("Only accepts conversation in u/a/u/a/u/a order.")
+                    msg_pairs.append((msg_list[idx][dataset_attr.content], msg_list[idx + 1][dataset_attr.content]))
+
+                if len(msg_pairs) != 0:
+                    outputs["prompt"].append(msg_pairs[-1][0])
+                    outputs["query"].append("")
+                    outputs["response"].append(msg_pairs[-1][1])
+                    outputs["history"].append(msg_pairs[:-1] if len(msg_pairs) > 1 else None)
+                    outputs["system"].append(examples[dataset_attr.system][i] if dataset_attr.system else "")
+
+            return outputs
+
+        if dataset_attr.formatting == "sharegpt": # convert format
+            column_names = list(next(iter(dataset)).keys())
+            kwargs = {}
+            if not data_args.streaming:
+                kwargs = dict(
+                    num_proc=data_args.preprocessing_num_workers,
+                    load_from_cache_file=(not data_args.overwrite_cache),
+                    desc="Converting format of dataset"
+                )
+
+            dataset = dataset.map(
+                convert_format,
+                batched=True,
+                remove_columns=column_names,
+                **kwargs
+            )
+        else:
+            for column_name in ["prompt", "query", "response", "history", "system"]: # align dataset
+                if getattr(dataset_attr, column_name) and getattr(dataset_attr, column_name) != column_name:
+                    dataset = dataset.rename_column(getattr(dataset_attr, column_name), column_name)
+
+        all_datasets.append(dataset)
+
+    if len(data_args.dataset_list) == 1:
+        return all_datasets[0]
+    elif data_args.mix_strategy == "concat":
+        if data_args.streaming:
+            logger.warning("The samples between different datasets will not be mixed in streaming mode.")
+        return concatenate_datasets(all_datasets)
+    elif data_args.mix_strategy.startswith("interleave"):
+        if not data_args.streaming:
+            logger.warning("We recommend using `mix_strategy=concat` in non-streaming mode.")
+        return interleave_datasets(
+            datasets=all_datasets,
+            probabilities=data_args.interleave_probs,
+            seed=data_args.seed,
+            stopping_strategy="first_exhausted" if data_args.mix_strategy.endswith("under") else "all_exhausted"
+        )
+    else:
+        raise ValueError("Unknown mixing strategy.")

LLM-Detector-V7-11w/src/llmtuner/data/preprocess.py

@@ -0,0 +1,272 @@
+import os
+import tiktoken
+from itertools import chain
+from typing import TYPE_CHECKING, Any, Dict, Generator, List, Literal, Tuple, Union
+
+from llmtuner.data.template import get_template_and_fix_tokenizer
+from llmtuner.extras.constants import IGNORE_INDEX
+from llmtuner.extras.logging import get_logger
+
+if TYPE_CHECKING:
+    from datasets import Dataset, IterableDataset
+    from transformers import Seq2SeqTrainingArguments
+    from transformers.tokenization_utils import PreTrainedTokenizer
+    from llmtuner.hparams import DataArguments
+
+
+logger = get_logger(__name__)
+
+
+def construct_example(examples: Dict[str, List[Any]]) -> Generator[Any, None, None]:
+    for i in range(len(examples["prompt"])):
+        query, response = examples["prompt"][i], examples["response"][i]
+        query = query + "\n" + examples["query"][i] if "query" in examples and examples["query"][i] else query
+        history = examples["history"][i] if "history" in examples else None
+        system = examples["system"][i] if "system" in examples else None
+        yield query, response, history, system
+
+
+def infer_max_len(source_len: int, target_len: int, data_args: "DataArguments") -> Tuple[int, int]:
+    max_target_len = int(data_args.cutoff_len * (target_len / (source_len + target_len)))
+    max_target_len = max(max_target_len, data_args.reserved_label_len)
+    max_source_len = data_args.cutoff_len - max_target_len
+    return max_source_len, max_target_len
+
+
+def preprocess_dataset(
+    dataset: Union["Dataset", "IterableDataset"],
+    tokenizer: "PreTrainedTokenizer",
+    data_args: "DataArguments",
+    training_args: "Seq2SeqTrainingArguments",
+    stage: Literal["pt", "sft", "rm", "ppo"]
+) -> Union["Dataset", "IterableDataset"]:
+    template = get_template_and_fix_tokenizer(data_args.template, tokenizer)
+
+    if data_args.cache_path is not None and os.path.exists(data_args.cache_path):
+        return dataset # already preprocessed
+
+    if data_args.train_on_prompt and template.efficient_eos:
+        raise ValueError("Current template does not support `train_on_prompt`.")
+
+    def preprocess_pretrain_dataset(examples: Dict[str, List[Any]]) -> Dict[str, List[List[int]]]:
+        # build grouped texts with format `X1 X2 X3 ...`
+        if isinstance(getattr(tokenizer, "tokenizer", None), tiktoken.Encoding): # for tiktoken tokenizer (Qwen)
+            kwargs = dict(allowed_special="all")
+        else:
+            kwargs = dict(add_special_tokens=True)
+
+        if hasattr(tokenizer, "add_eos_token"): # for LLaMA tokenizer
+            add_eos_token_flag = getattr(tokenizer, "add_eos_token")
+            setattr(tokenizer, "add_eos_token", True)
+
+        tokenized_examples = tokenizer(examples["prompt"], **kwargs)
+        concatenated_examples = {k: list(chain(*tokenized_examples[k])) for k in tokenized_examples.keys()}
+        total_length = len(concatenated_examples[list(concatenated_examples.keys())[0]])
+        block_size = data_args.cutoff_len
+        # we drop the small remainder, and if the total_length < block_size, we exclude this batch
+        total_length = (total_length // block_size) * block_size
+        # split by chunks of cutoff_len
+        result = {
+            k: [t[i: i + block_size] for i in range(0, total_length, block_size)]
+            for k, t in concatenated_examples.items()
+        }
+        # make sure the saved tokenizer is the same as the original one
+        if hasattr(tokenizer, "add_eos_token"):
+            setattr(tokenizer, "add_eos_token", add_eos_token_flag)
+        return result
+
+    def preprocess_supervised_dataset(examples: Dict[str, List[Any]]) -> Dict[str, List[List[int]]]:
+        # build inputs with format `<bos> X Y <eos>` and labels with format `<ignore> ... <ignore> Y <eos>`
+        # for multiturn examples, we only mask the prompt part in each prompt-response pair.
+        model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
+
+        for query, response, history, system in construct_example(examples):
+            if not (isinstance(query, str) and isinstance(response, str) and query != "" and response != ""):
+                continue
+
+            input_ids, labels = [], []
+            for turn_idx, (source_ids, target_ids) in enumerate(template.encode_multiturn(
+                tokenizer, query, response, history, system
+            )):
+                source_len, target_len = len(source_ids), len(target_ids)
+                max_source_len, max_target_len = infer_max_len(source_len, target_len, data_args)
+                if source_len > max_source_len:
+                    source_ids = source_ids[:max_source_len]
+                if target_len > max_target_len:
+                    target_ids = target_ids[:max_target_len]
+
+                if data_args.train_on_prompt:
+                    source_mask = source_ids
+                elif turn_idx != 0 and template.efficient_eos:
+                    source_mask = [tokenizer.eos_token_id] + [IGNORE_INDEX] * (len(source_ids) - 1)
+                else:
+                    source_mask = [IGNORE_INDEX] * len(source_ids)
+
+                input_ids += source_ids + target_ids
+                labels += source_mask + target_ids
+
+            if template.efficient_eos:
+                input_ids += [tokenizer.eos_token_id]
+                labels += [tokenizer.eos_token_id]
+
+            if len(input_ids) > data_args.cutoff_len:
+                input_ids = input_ids[:data_args.cutoff_len]
+                labels = labels[:data_args.cutoff_len]
+
+            model_inputs["input_ids"].append(input_ids)
+            model_inputs["attention_mask"].append([1] * len(input_ids))
+            model_inputs["labels"].append(labels)
+
+        return model_inputs
+
+    def preprocess_packed_supervised_dataset(examples: Dict[str, List[Any]]) -> Dict[str, List[List[int]]]:
+        # build inputs with format `<bos> X1 Y1 <eos> <bos> X2 Y2 <eos>`
+        # and labels with format `<ignore> ... <ignore> Y1 <eos> <ignore> ... <ignore> Y2 <eos>`
+        model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
+        input_ids, labels = [], []
+        for query, response, history, system in construct_example(examples):
+            if not (isinstance(query, str) and isinstance(response, str) and query != "" and response != ""):
+                continue
+
+            for turn_idx, (source_ids, target_ids) in enumerate(template.encode_multiturn(
+                tokenizer, query, response, history, system
+            )):
+                if data_args.train_on_prompt:
+                    source_mask = source_ids
+                elif turn_idx != 0 and template.efficient_eos:
+                    source_mask = [tokenizer.eos_token_id] + [IGNORE_INDEX] * (len(source_ids) - 1)
+                else:
+                    source_mask = [IGNORE_INDEX] * len(source_ids)
+                input_ids += source_ids + target_ids
+                labels += source_mask + target_ids
+
+        if template.efficient_eos:
+            input_ids += [tokenizer.eos_token_id]
+            labels += [tokenizer.eos_token_id]
+
+        total_length = len(input_ids)
+        block_size = data_args.cutoff_len
+        # we drop the small remainder, and if the total_length < block_size, we exclude this batch
+        total_length = (total_length // block_size) * block_size
+        # split by chunks of cutoff_len
+        for i in range(0, total_length, block_size):
+            model_inputs["input_ids"].append(input_ids[i: i + block_size])
+            model_inputs["attention_mask"].append([1] * block_size)
+            model_inputs["labels"].append(labels[i: i + block_size])
+
+        return model_inputs
+
+    def preprocess_unsupervised_dataset(examples: Dict[str, List[Any]]) -> Dict[str, List[List[int]]]:
+        # build inputs with format `<bos> X` and labels with format `Y <eos>`
+        model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
+
+        for query, response, history, system in construct_example(examples):
+            if not (isinstance(query, str) and query != ""):
+                continue
+
+            input_ids, labels = template.encode_oneturn(tokenizer, query, response, history, system)
+
+            if template.efficient_eos:
+                labels += [tokenizer.eos_token_id]
+
+            if len(input_ids) > data_args.cutoff_len:
+                input_ids = input_ids[:data_args.cutoff_len]
+            if len(labels) > data_args.cutoff_len:
+                labels = labels[:data_args.cutoff_len]
+
+            model_inputs["input_ids"].append(input_ids)
+            model_inputs["attention_mask"].append([1] * len(input_ids))
+            model_inputs["labels"].append(labels)
+
+        return model_inputs
+
+    def preprocess_pairwise_dataset(examples: Dict[str, List[Any]]) -> Dict[str, List[List[int]]]:
+        # build input pairs with format `<bos> X`, `Y1 <eos>` and `Y2 <eos>`
+        model_inputs = {"prompt_ids": [], "chosen_ids": [], "rejected_ids": []}
+        for query, response, history, system in construct_example(examples):
+            if not (isinstance(query, str) and isinstance(response, list) and query != "" and len(response) > 1):
+                continue
+
+            prompt_ids, chosen_ids = template.encode_oneturn(tokenizer, query, response[0], history, system)
+            _, rejected_ids = template.encode_oneturn(tokenizer, query, response[1], history, system)
+
+            if template.efficient_eos:
+                chosen_ids += [tokenizer.eos_token_id]
+                rejected_ids += [tokenizer.eos_token_id]
+
+            source_len, target_len = len(prompt_ids), max(len(chosen_ids), len(rejected_ids))
+            max_source_len, max_target_len = infer_max_len(source_len, target_len, data_args)
+            if source_len > max_source_len:
+                prompt_ids = prompt_ids[:max_source_len]
+            if target_len > max_target_len:
+                chosen_ids = chosen_ids[:max_target_len]
+                rejected_ids = rejected_ids[:max_target_len]
+
+            model_inputs["prompt_ids"].append(prompt_ids)
+            model_inputs["chosen_ids"].append(chosen_ids)
+            model_inputs["rejected_ids"].append(rejected_ids)
+
+        return model_inputs
+
+    def print_supervised_dataset_example(example: Dict[str, List[int]]) -> None:
+        print("input_ids:\n{}".format(example["input_ids"]))
+        print("inputs:\n{}".format(tokenizer.decode(example["input_ids"], skip_special_tokens=False)))
+        print("label_ids:\n{}".format(example["labels"]))
+        print("labels:\n{}".format(
+            tokenizer.decode(list(filter(lambda x: x != IGNORE_INDEX, example["labels"])), skip_special_tokens=False)
+        ))
+
+    def print_pairwise_dataset_example(example: Dict[str, List[int]]) -> None:
+        print("prompt_ids:\n{}".format(example["prompt_ids"]))
+        print("prompt:\n{}".format(tokenizer.decode(example["prompt_ids"], skip_special_tokens=False)))
+        print("chosen_ids:\n{}".format(example["chosen_ids"]))
+        print("chosen:\n{}".format(tokenizer.decode(example["chosen_ids"], skip_special_tokens=False)))
+        print("rejected_ids:\n{}".format(example["rejected_ids"]))
+        print("rejected:\n{}".format(tokenizer.decode(example["rejected_ids"], skip_special_tokens=False)))
+
+    def print_unsupervised_dataset_example(example: Dict[str, List[int]]) -> None:
+        print("input_ids:\n{}".format(example["input_ids"]))
+        print("inputs:\n{}".format(tokenizer.decode(example["input_ids"], skip_special_tokens=False)))
+
+    if stage == "pt":
+        preprocess_func = preprocess_pretrain_dataset
+        print_function = print_unsupervised_dataset_example
+    elif stage == "sft" and not training_args.predict_with_generate:
+        preprocess_func = preprocess_packed_supervised_dataset if data_args.sft_packing else preprocess_supervised_dataset
+        print_function = print_supervised_dataset_example
+    elif stage == "rm":
+        preprocess_func = preprocess_pairwise_dataset
+        print_function = print_pairwise_dataset_example
+    else:
+        preprocess_func = preprocess_unsupervised_dataset
+        print_function = print_unsupervised_dataset_example
+
+    with training_args.main_process_first(desc="dataset map pre-processing"):
+        column_names = list(next(iter(dataset)).keys())
+        kwargs = {}
+        if not data_args.streaming:
+            kwargs = dict(
+                num_proc=data_args.preprocessing_num_workers,
+                load_from_cache_file=(not data_args.overwrite_cache),
+                desc="Running tokenizer on dataset"
+            )
+
+        dataset = dataset.map(
+            preprocess_func,
+            batched=True,
+            remove_columns=column_names,
+            **kwargs
+        )
+
+        if data_args.cache_path is not None and not os.path.exists(data_args.cache_path):
+            if training_args.should_save:
+                dataset.save_to_disk(data_args.cache_path)
+                logger.info("Dataset cache saved at {}.".format(data_args.cache_path))
+
+        if training_args.should_log:
+            try:
+                print_function(next(iter(dataset)))
+            except StopIteration:
+                raise RuntimeError("Empty dataset!")
+
+        return dataset

LLM-Detector-V7-11w/src/llmtuner/data/template.py

@@ -0,0 +1,815 @@
+import tiktoken
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Union
+
+from llmtuner.extras.logging import get_logger
+
+if TYPE_CHECKING:
+    from transformers import PreTrainedTokenizer
+
+
+logger = get_logger(__name__)
+
+
+@dataclass
+class Template:
+
+    prefix: List[Union[str, Dict[str, str]]]
+    prompt: List[Union[str, Dict[str, str]]]
+    system: str
+    sep: List[Union[str, Dict[str, str]]]
+    stop_words: List[str]
+    use_history: bool
+    efficient_eos: bool
+    replace_eos: bool
+
+    def encode_oneturn(
+        self,
+        tokenizer: "PreTrainedTokenizer",
+        query: str,
+        resp: str,
+        history: Optional[List[Tuple[str, str]]] = None,
+        system: Optional[str] = None
+    ) -> Tuple[List[int], List[int]]:
+        r"""
+        Returns a single pair of token ids representing prompt and response respectively.
+        """
+        system, history = self._format(query, resp, history, system)
+        encoded_pairs = self._encode(tokenizer, system, history)
+        prompt_ids = []
+        for query_ids, resp_ids in encoded_pairs[:-1]:
+            prompt_ids = prompt_ids + query_ids + resp_ids
+        prompt_ids = prompt_ids + encoded_pairs[-1][0]
+        answer_ids = encoded_pairs[-1][1]
+        return prompt_ids, answer_ids
+
+    def encode_multiturn(
+        self,
+        tokenizer: "PreTrainedTokenizer",
+        query: str,
+        resp: str,
+        history: Optional[List[Tuple[str, str]]] = None,
+        system: Optional[str] = None
+    ) -> List[Tuple[List[int], List[int]]]:
+        r"""
+        Returns multiple pairs of token ids representing prompts and responses respectively.
+        """
+        system, history = self._format(query, resp, history, system)
+        encoded_pairs = self._encode(tokenizer, system, history)
+        return encoded_pairs
+
+    def _format(
+        self,
+        query: str,
+        resp: str,
+        history: Optional[List[Tuple[str, str]]] = None,
+        system: Optional[str] = None
+    ) -> Tuple[str, List[Tuple[str, str]]]:
+        r"""
+        Aligns inputs to the standard format.
+        """
+        system = system or self.system # use system if provided
+        history = history if (history and self.use_history) else []
+        history = history + [(query, resp)]
+        return system, history
+
+    def _get_special_ids(
+        self,
+        tokenizer: "PreTrainedTokenizer"
+    ) -> Tuple[List[int], List[int]]:
+        if tokenizer.bos_token_id is not None and getattr(tokenizer, "add_bos_token", True):
+            bos_ids = [tokenizer.bos_token_id]
+        else: # baichuan, gpt2, qwen, yi models have no bos token
+            bos_ids = []
+
+        if tokenizer.eos_token_id is None:
+            raise ValueError("EOS token is required.")
+
+        if self.efficient_eos:
+            eos_ids = []
+        else:
+            eos_ids = [tokenizer.eos_token_id]
+
+        return bos_ids, eos_ids
+
+    def _encode(
+        self,
+        tokenizer: "PreTrainedTokenizer",
+        system: str,
+        history: List[Tuple[str, str]]
+    ) -> List[Tuple[List[int], List[int]]]:
+        r"""
+        Encodes formatted inputs to pairs of token ids.
+        Turn 0: bos + prefix + sep + query    resp + eos
+        Turn t: sep + bos + query             resp + eos
+        """
+        bos_ids, eos_ids = self._get_special_ids(tokenizer)
+        sep_ids = self._convert_inputs_to_ids(tokenizer, context=self.sep)
+        encoded_pairs = []
+        for turn_idx, (query, resp) in enumerate(history):
+            if turn_idx == 0:
+                prefix_ids = self._convert_inputs_to_ids(tokenizer, context=self.prefix, system=system)
+                if len(prefix_ids) != 0: # has prefix
+                    prefix_ids = bos_ids + prefix_ids + sep_ids
+                else:
+                    prefix_ids = bos_ids
+            else:
+                prefix_ids = sep_ids + bos_ids
+
+            query_ids = self._convert_inputs_to_ids(tokenizer, context=self.prompt, query=query, idx=str(turn_idx+1))
+            resp_ids = self._convert_inputs_to_ids(tokenizer, context=[resp])
+            encoded_pairs.append((prefix_ids + query_ids, resp_ids + eos_ids))
+        return encoded_pairs
+
+    def _convert_inputs_to_ids(
+        self,
+        tokenizer: "PreTrainedTokenizer",
+        context: List[Union[str, Dict[str, str]]],
+        system: Optional[str] = None,
+        query: Optional[str] = None,
+        idx: Optional[str] = None
+    ) -> List[int]:
+        r"""
+        Converts context to token ids.
+        """
+        if isinstance(getattr(tokenizer, "tokenizer", None), tiktoken.Encoding): # for tiktoken tokenizer (Qwen)
+            kwargs = dict(allowed_special="all")
+        else:
+            kwargs = dict(add_special_tokens=False)
+
+        token_ids = []
+        for elem in context:
+            if isinstance(elem, str):
+                elem = elem.replace("{{system}}", system, 1) if system is not None else elem
+                elem = elem.replace("{{query}}", query, 1) if query is not None else elem
+                elem = elem.replace("{{idx}}", idx, 1) if idx is not None else elem
+                if len(elem) != 0:
+                    token_ids = token_ids + tokenizer.encode(elem, **kwargs)
+            elif isinstance(elem, dict):
+                token_ids = token_ids + [tokenizer.convert_tokens_to_ids(elem.get("token"))]
+            else:
+                raise ValueError("Input must be string or dict[str, str], got {}".format(type(elem)))
+
+        return token_ids
+
+
+@dataclass
+class Llama2Template(Template):
+
+    def _encode(
+        self,
+        tokenizer: "PreTrainedTokenizer",
+        system: str,
+        history: List[Tuple[str, str]]
+    ) -> List[Tuple[List[int], List[int]]]:
+        r"""
+        Encodes formatted inputs to pairs of token ids.
+        Turn 0: bos + prefix + query    resp + eos
+        Turn t: bos + query             resp + eos
+        """
+        bos_ids, eos_ids = self._get_special_ids(tokenizer)
+        encoded_pairs = []
+        for turn_idx, (query, resp) in enumerate(history):
+            if turn_idx == 0: # llama2 template has no sep_ids
+                query = self.prefix[0].replace("{{system}}", system) + query
+            query_ids = self._convert_inputs_to_ids(tokenizer, context=self.prompt, query=query)
+            resp_ids = self._convert_inputs_to_ids(tokenizer, context=[resp])
+            encoded_pairs.append((bos_ids + query_ids, resp_ids + eos_ids))
+        return encoded_pairs
+
+
+templates: Dict[str, Template] = {}
+
+
+def register_template(
+    name: str,
+    prefix: List[Union[str, Dict[str, str]]],
+    prompt: List[Union[str, Dict[str, str]]],
+    system: str,
+    sep: List[Union[str, Dict[str, str]]],
+    stop_words: Optional[List[str]] = [],
+    use_history: Optional[bool] = True,
+    efficient_eos: Optional[bool] = False,
+    replace_eos: Optional[bool] = False
+) -> None:
+    template_class = Llama2Template if name.startswith("llama2") else Template
+    templates[name] = template_class(
+        prefix=prefix,
+        prompt=prompt,
+        system=system,
+        sep=sep,
+        stop_words=stop_words,
+        use_history=use_history,
+        efficient_eos=efficient_eos,
+        replace_eos=replace_eos
+    )
+
+
+def get_template_and_fix_tokenizer(
+    name: str,
+    tokenizer: "PreTrainedTokenizer"
+) -> Template:
+    if tokenizer.eos_token_id is None:
+        tokenizer.eos_token = "<|endoftext|>"
+        logger.info("Add eos token: {}".format(tokenizer.eos_token))
+
+    if tokenizer.pad_token_id is None:
+        tokenizer.pad_token = tokenizer.eos_token
+        logger.info("Add pad token: {}".format(tokenizer.pad_token))
+
+    if name is None: # for pre-training
+        return None
+
+    template = templates.get(name, None)
+    assert template is not None, "Template {} does not exist.".format(name)
+
+    stop_words = template.stop_words
+    if template.replace_eos:
+        if not stop_words:
+            raise ValueError("Stop words are required to replace the EOS token.")
+
+        tokenizer.eos_token = stop_words[0]
+        stop_words = stop_words[1:]
+        logger.info("Replace eos token: {}".format(tokenizer.eos_token))
+
+    if stop_words:
+        tokenizer.add_special_tokens(
+            dict(additional_special_tokens=stop_words),
+            replace_additional_special_tokens=False
+        )
+        logger.info("Add {} to stop words.".format(",".join(stop_words)))
+
+    return template
+
+
+register_template(
+    name="alpaca",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "### Instruction:\n{{query}}\n\n### Response:\n"
+    ],
+    system=(
+        "Below is an instruction that describes a task. "
+        "Write a response that appropriately completes the request."
+    ),
+    sep=[
+        "\n\n"
+    ]
+)
+
+
+register_template(
+    name="aquila",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "Human: {{query}}###Assistant:"
+    ],
+    system=(
+        "A chat between a curious human and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the human's questions."
+    ),
+    sep=[
+        "###"
+    ],
+    stop_words=[
+        "</s>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="baichuan",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        {"token": "<reserved_102>"}, # user token
+        "{{query}}",
+        {"token": "<reserved_103>"}  # assistant token
+    ],
+    system="",
+    sep=[],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="baichuan2",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        {"token": "<reserved_106>"}, # user token
+        "{{query}}",
+        {"token": "<reserved_107>"}  # assistant token
+    ],
+    system="",
+    sep=[],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="belle",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "Human: {{query}}\n\nBelle: "
+    ],
+    system="",
+    sep=[
+        "\n\n"
+    ]
+)
+
+
+register_template(
+    name="bluelm",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        {"token": "[|Human|]:"},
+        "{{query}}",
+        {"token": "[|AI|]:"}
+    ],
+    system="",
+    sep=[]
+)
+
+
+register_template(
+    name="chatglm2",
+    prefix=[
+        {"token": "[gMASK]"},
+        {"token": "sop"},
+        "{{system}}"
+    ],
+    prompt=[
+        "[Round {{idx}}]\n\n问：{{query}}\n\n答："
+    ],
+    system="",
+    sep=[
+        "\n\n"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="chatglm3",
+    prefix=[
+        {"token": "[gMASK]"},
+        {"token": "sop"},
+        {"token": "<|system|>"},
+        "\n",
+        "{{system}}"
+    ],
+    prompt=[
+        {"token": "<|user|>"},
+        "\n",
+        "{{query}}",
+        {"token": "<|assistant|>"},
+        "\n" # add an extra newline to avoid error in ChatGLM's process_response method
+    ],
+    system=(
+        "You are ChatGLM3, a large language model trained by Zhipu.AI. "
+        "Follow the user's instructions carefully. Respond using markdown."
+    ),
+    sep=[],
+    stop_words=[
+        "<|user|>",
+        "<|observation|>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="chatglm3_raw", # the raw template for tool tuning
+    prefix=[
+        {"token": "[gMASK]"},
+        {"token": "sop"},
+        {"token": "<|system|>"},
+        "\n",
+        "{{system}}"
+    ],
+    prompt=[
+        {"token": "<|user|>"},
+        "\n",
+        "{{query}}",
+        {"token": "<|assistant|>"}
+    ],
+    system=(
+        "You are ChatGLM3, a large language model trained by Zhipu.AI. "
+        "Follow the user's instructions carefully. Respond using markdown."
+    ),
+    sep=[],
+    stop_words=[
+        "<|user|>",
+        "<|observation|>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="codegeex2",
+    prefix=[
+        {"token": "[gMASK]"},
+        {"token": "sop"},
+        "{{system}}"
+    ],
+    prompt=[
+        "{{query}}"
+    ],
+    system="",
+    sep=[]
+)
+
+
+register_template(
+    name="deepseek",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "User: {{query}}\n\nAssistant:"
+    ],
+    system="",
+    sep=[]
+)
+
+
+register_template(
+    name="deepseekcoder",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "### Instruction:\n{{query}}\n### Response:\n"
+    ],
+    system=(
+        "You are an AI programming assistant, utilizing the Deepseek Coder model, "
+        "developed by Deepseek Company, and you only answer questions related to computer science. "
+        "For politically sensitive questions, security and privacy issues, "
+        "and other non-computer science questions, you will refuse to answer\n"
+    ),
+    sep=[
+        "\n",
+        {"token": "<|EOT|>"},
+        "\n"
+    ],
+    stop_words=[
+        "<|EOT|>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="default",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "Human: {{query}}\nAssistant:"
+    ],
+    system=(
+        "A chat between a curious user and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+    ),
+    sep=[
+        "\n"
+    ]
+)
+
+
+register_template(
+    name="falcon",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "User: {{query}}\nFalcon:"
+    ],
+    system="",
+    sep=[
+        "\n"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="intern",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "<|User|>:{{query}}",
+        {"token": "<eoh>"},
+        "\n<|Bot|>:"
+    ],
+    system="",
+    sep=[
+        {"token": "<eoa>"},
+        "\n"
+    ],
+    stop_words=[
+        "<eoa>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="llama2",
+    prefix=[
+        "<<SYS>>\n{{system}}\n<</SYS>>\n\n"
+    ],
+    prompt=[
+        "[INST] {{query}} [/INST]"
+    ],
+    system=(
+        "You are a helpful, respectful and honest assistant. "
+        "Always answer as helpfully as possible, while being safe. "
+        "Your answers should not include any harmful, unethical, "
+        "racist, sexist, toxic, dangerous, or illegal content. "
+        "Please ensure that your responses are socially unbiased and positive in nature.\n\n"
+        "If a question does not make any sense, or is not factually coherent, "
+        "explain why instead of answering something not correct. "
+        "If you don't know the answer to a question, please don't share false information."
+    ),
+    sep=[]
+)
+
+
+register_template(
+    name="llama2_zh",
+    prefix=[
+        "<<SYS>>\n{{system}}\n<</SYS>>\n\n"
+    ],
+    prompt=[
+        "[INST] {{query}} [/INST]"
+    ],
+    system="You are a helpful assistant. 你是一个乐于助人的助手。",
+    sep=[]
+)
+
+
+register_template(
+    name="mistral",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "[INST] {{query}} [/INST]"
+    ],
+    system="",
+    sep=[]
+)
+
+
+register_template(
+    name="openchat",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "GPT4 Correct User: {{query}}",
+        {"token": "<|end_of_turn|>"},
+        "GPT4 Correct Assistant:"
+    ],
+    system="",
+    sep=[
+        {"token": "<|end_of_turn|>"}
+    ],
+    stop_words=[
+        "<|end_of_turn|>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="qwen",
+    prefix=[
+        "<|im_start|>system\n{{system}}<|im_end|>"
+    ],
+    prompt=[
+        "<|im_start|>user\n{{query}}<|im_end|>\n<|im_start|>assistant\n"
+    ],
+    system="You are a helpful assistant.",
+    sep=[
+        "\n"
+    ],
+    stop_words=[
+        "<|im_end|>"
+    ],
+    replace_eos=True
+)
+
+
+register_template(
+    name="solar",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "### User:\n{{query}}\n\n### Assistant:\n"
+    ],
+    system="",
+    sep=[]
+)
+
+
+register_template(
+    name="starchat",
+    prefix=[
+        {"token": "<|system|>"},
+        "\n{{system}}",
+    ],
+    prompt=[
+        {"token": "<|user|>"},
+        "\n{{query}}",
+        {"token": "<|end|>"},
+        "\n",
+        {"token": "<|assistant|>"}
+    ],
+    system="",
+    sep=[
+        {"token": "<|end|>"},
+        "\n"
+    ],
+    stop_words=[
+        "<|end|>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="vanilla",
+    prefix=[],
+    prompt=[
+        "{{query}}"
+    ],
+    system="",
+    sep=[],
+    use_history=False
+)
+
+
+register_template(
+    name="vicuna",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "USER: {{query}} ASSISTANT:"
+    ],
+    system=(
+        "A chat between a curious user and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+    ),
+    sep=[]
+)
+
+
+register_template(
+    name="xuanyuan",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "Human: {{query}} Assistant:"
+    ],
+    system=(
+        "以下是用户和人工智能助手之间的对话。用户以Human开头，人工智能助手以Assistant开头，"
+        "会对人类提出的问题给出有帮助、高质量、详细和礼貌的回答，并且总是拒绝参与与不道德、"
+        "不安全、有争议、政治敏感等相关的话题、问题和指示。\n"
+    ),
+    sep=[]
+)
+
+
+register_template(
+    name="xverse",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "Human: {{query}}\n\nAssistant: "
+    ],
+    system="",
+    sep=[]
+)
+
+
+register_template(
+    name="yayi",
+    prefix=[
+        {"token": "<|System|>"},
+        ":\n{{system}}"
+    ],
+    prompt=[
+        {"token": "<|Human|>"},
+        ":\n{{query}}\n\n",
+        {"token": "<|YaYi|>"},
+        ":"
+    ],
+    system=(
+        "You are a helpful, respectful and honest assistant named YaYi "
+        "developed by Beijing Wenge Technology Co.,Ltd. "
+        "Always answer as helpfully as possible, while being safe.  "
+        "Your answers should not include any harmful, unethical, "
+        "racist, sexist, toxic, dangerous, or illegal content. "
+        "Please ensure that your responses are socially unbiased and positive in nature.\n\n"
+        "If a question does not make any sense, or is not factually coherent, "
+        "explain why instead of answering something not correct. "
+        "If you don't know the answer to a question, please don't share false information."
+    ),
+    sep=[
+        "\n\n"
+    ],
+    stop_words=[
+        "<|End|>"
+    ]
+)
+
+
+register_template(
+    name="yi",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "<|im_start|>user\n{{query}}<|im_end|>\n<|im_start|>assistant\n"
+    ],
+    system="",
+    sep=[
+        "\n"
+    ],
+    stop_words=[
+        "<|im_end|>"
+    ],
+    replace_eos=True
+)
+
+
+register_template(
+    name="yuan",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        "{{query}}",
+        {"token": "<sep>"}
+    ],
+    system="",
+    sep=[
+        "\n"
+    ],
+    stop_words=[
+        "<eod>"
+    ],
+    replace_eos=True
+)
+
+
+register_template(
+    name="zephyr",
+    prefix=[
+        "<|system|>\n{{system}}</s>",
+    ],
+    prompt=[
+        "<|user|>\n{{query}}</s><|assistant|>"
+    ],
+    system="You are a friendly chatbot who always responds in the style of a pirate",
+    sep=[]
+)
+
+
+register_template(
+    name="ziya",
+    prefix=[
+        "{{system}}"
+    ],
+    prompt=[
+        {"token": "<human>"},
+        ":{{query}}\n",
+        {"token": "<bot>"},
+        ":"
+    ],
+    system="",
+    sep=[
+        "\n"
+    ]
+)

LLM-Detector-V7-11w/src/llmtuner/data/utils.py

@@ -0,0 +1,51 @@
+import hashlib
+from typing import TYPE_CHECKING, Dict, List, Optional, Union
+
+from llmtuner.extras.logging import get_logger
+
+if TYPE_CHECKING:
+    from datasets import Dataset, IterableDataset
+    from transformers import TrainingArguments
+    from llmtuner.hparams import DataArguments
+
+
+logger = get_logger(__name__)
+
+
+def checksum(data_files: List[str], file_sha1: Optional[str] = None) -> None:
+    if file_sha1 is None:
+        logger.warning("Checksum failed: missing SHA-1 hash value in dataset_info.json.")
+        return
+
+    if len(data_files) != 1:
+        logger.warning("Checksum failed: too many files.")
+        return
+
+    with open(data_files[0], "rb") as f:
+        sha1 = hashlib.sha1(f.read()).hexdigest()
+        if sha1 != file_sha1:
+            logger.warning("Checksum failed: mismatched SHA-1 hash value at {}.".format(data_files[0]))
+
+
+def split_dataset(
+    dataset: Union["Dataset", "IterableDataset"],
+    data_args: "DataArguments",
+    training_args: "TrainingArguments"
+) -> Dict[str, "Dataset"]:
+    if training_args.do_train:
+        if data_args.val_size > 1e-6: # Split the dataset
+            if data_args.streaming:
+                val_set = dataset.take(int(data_args.val_size))
+                train_set = dataset.skip(int(data_args.val_size))
+                dataset = dataset.shuffle(buffer_size=data_args.buffer_size, seed=training_args.seed)
+                return {"train_dataset": train_set, "eval_dataset": val_set}
+            else:
+                val_size = int(data_args.val_size) if data_args.val_size > 1 else data_args.val_size
+                dataset = dataset.train_test_split(test_size=val_size, seed=training_args.seed)
+                return {"train_dataset": dataset["train"], "eval_dataset": dataset["test"]}
+        else:
+            if data_args.streaming:
+                dataset = dataset.shuffle(buffer_size=data_args.buffer_size, seed=training_args.seed)
+            return {"train_dataset": dataset}
+    else: # do_eval or do_predict
+        return {"eval_dataset": dataset}

LLM-Detector-V7-11w/src/llmtuner/eval/__init__.py

@@ -0,0 +1 @@
+from llmtuner.eval.evaluator import Evaluator

LLM-Detector-V7-11w/src/llmtuner/eval/evaluator.py

@@ -0,0 +1,118 @@
+# Inspired by: https://github.com/hendrycks/test/blob/master/evaluate_flan.py
+
+import os
+import json
+import torch
+import tiktoken
+import numpy as np
+from tqdm import tqdm, trange
+from typing import Any, Dict, List, Optional
+
+from datasets import load_dataset
+from transformers.utils import cached_file
+
+from llmtuner.data.template import get_template_and_fix_tokenizer
+from llmtuner.eval.template import get_eval_template
+from llmtuner.extras.constants import CHOICES, SUBJECTS
+from llmtuner.model import dispatch_model, get_eval_args, load_model_and_tokenizer
+
+
+class Evaluator:
+
+    def __init__(self, args: Optional[Dict[str, Any]] = None) -> None:
+        self.model_args, self.data_args, self.eval_args, finetuning_args = get_eval_args(args)
+        self.model, self.tokenizer = load_model_and_tokenizer(self.model_args, finetuning_args)
+        self.tokenizer.padding_side = "right" # avoid overflow issue in batched inference for llama2
+        self.model = dispatch_model(self.model)
+        self.template = get_template_and_fix_tokenizer(self.data_args.template, self.tokenizer)
+        self.eval_template = get_eval_template(self.eval_args.lang)
+        self.choice_inputs = self._encode_choices()
+
+    def _encode_choices(self) -> List[int]:
+        if isinstance(getattr(self.tokenizer, "tokenizer", None), tiktoken.Encoding): # for tiktoken tokenizer (Qwen)
+            kwargs = dict(allowed_special="all")
+        else:
+            kwargs = dict(add_special_tokens=False)
+
+        return [self.tokenizer.encode(self.eval_template.prefix + ch, **kwargs)[-1] for ch in CHOICES]
+
+    @torch.inference_mode()
+    def batch_inference(self, batch_input: Dict[str, torch.Tensor]) -> List[str]:
+        logits = self.model(**batch_input).logits
+        lengths = torch.sum(batch_input["attention_mask"], dim=-1)
+        word_probs = torch.stack([logits[i, lengths[i] - 1] for i in range(len(lengths))], dim=0)
+        choice_probs = torch.nn.functional.softmax(word_probs[:, self.choice_inputs], dim=-1).detach()
+        return [chr(ord("A") + offset.item()) for offset in torch.argmax(choice_probs, dim=-1)]
+
+    def eval(self) -> None:
+        mapping = cached_file(
+            path_or_repo_id = os.path.join(self.eval_args.task_dir, self.eval_args.task),
+            filename="mapping.json",
+            cache_dir=self.model_args.cache_dir,
+            token=self.model_args.hf_hub_token
+        )
+
+        with open(mapping, "r", encoding="utf-8") as f:
+            categorys: Dict[str, Dict[str, str]] = json.load(f)
+
+        category_corrects = {subj: np.array([], dtype="bool") for subj in SUBJECTS}
+        pbar = tqdm(categorys.keys(), desc="Processing subjects", position=0)
+        results = {}
+        for subject in pbar:
+            dataset = load_dataset(
+                path=os.path.join(self.eval_args.task_dir, self.eval_args.task),
+                name=subject,
+                cache_dir=self.model_args.cache_dir,
+                download_mode=self.eval_args.download_mode,
+                token=self.model_args.hf_hub_token
+            )
+            pbar.set_postfix_str(categorys[subject]["name"])
+            inputs, outputs, labels = [], [], []
+            for i in trange(len(dataset[self.data_args.split]), desc="Formatting batches", position=1, leave=False):
+                support_set = dataset["train"].shuffle().select(range(min(self.eval_args.n_shot, len(dataset["train"]))))
+                query, resp, history = self.eval_template.format_example(
+                    target_data=dataset[self.data_args.split][i],
+                    support_set=support_set,
+                    subject_name=categorys[subject]["name"],
+                    use_history=self.template.use_history
+                )
+                input_ids, _ = self.template.encode_oneturn(
+                    tokenizer=self.tokenizer, query=query, resp=resp, history=history
+                )
+                inputs.append({"input_ids": input_ids, "attention_mask": [1] * len(input_ids)})
+                labels.append(resp)
+
+            for i in trange(0, len(inputs), self.eval_args.batch_size, desc="Predicting batches", position=1, leave=False):
+                batch_input = self.tokenizer.pad(
+                    inputs[i : i + self.eval_args.batch_size], return_attention_mask=True, return_tensors="pt"
+                ).to(self.model.device)
+                preds = self.batch_inference(batch_input)
+                outputs += preds
+
+            corrects = (np.array(outputs) == np.array(labels))
+            category_name = categorys[subject]["category"]
+            category_corrects[category_name] = np.concatenate([category_corrects[category_name], corrects], axis=0)
+            category_corrects["Average"] = np.concatenate([category_corrects["Average"], corrects], axis=0)
+            results[subject] = {str(i): outputs[i] for i in range(len(outputs))}
+
+        pbar.close()
+        self._save_results(category_corrects, results)
+
+    def _save_results(self, category_corrects: Dict[str, np.ndarray], results: Dict[str, Dict[int, str]]) -> None:
+        score_info = "\n".join([
+            "{:>15}: {:.2f}".format(category_name, 100 * np.mean(category_correct))
+            for category_name, category_correct in category_corrects.items() if len(category_correct)
+        ])
+        print(score_info)
+        if self.eval_args.save_dir is not None:
+            os.makedirs(self.eval_args.save_dir, exist_ok=False)
+            with open(os.path.join(self.eval_args.save_dir, "results.json"), "w", encoding="utf-8", newline="\n") as f:
+                json.dump(results, f, indent=2)
+
+            with open(os.path.join(self.eval_args.save_dir, "results.log"), "w", encoding="utf-8", newline="\n") as f:
+                f.write(score_info)
+
+
+if __name__ == "__main__":
+    evaluator = Evaluator()
+    evaluator.eval()

LLM-Detector-V7-11w/src/llmtuner/eval/template.py

@@ -0,0 +1,86 @@
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Dict, List, Tuple
+
+from llmtuner.extras.constants import CHOICES
+
+if TYPE_CHECKING:
+    from datasets import Dataset
+
+
+@dataclass
+class EvalTemplate:
+
+    system: str
+    choice: str
+    answer: str
+    prefix: str
+
+    def parse_example(
+        self,
+        example: Dict[str, str]
+    ) -> Tuple[str, str]:
+        candidates = [self.choice.format(choice=ch, content=example[ch]) for ch in CHOICES if ch in example]
+        return "".join([example["question"]] + candidates + [self.answer]), example["answer"]
+
+    def format_example(
+        self,
+        target_data: Dict[str, str],
+        support_set: "Dataset",
+        subject_name: str,
+        use_history: bool
+    ) -> Tuple[str, str, List[Tuple[str, str]]]:
+        query, resp = self.parse_example(target_data)
+        history = [self.parse_example(support_set[k]) for k in range(len(support_set))]
+
+        if len(history):
+            temp = history.pop(0)
+            history.insert(0, (self.system.format(subject=subject_name) + temp[0], temp[1]))
+        else:
+            query = self.system.format(subject=subject_name) + query
+
+        if not use_history:
+            query = "\n\n".join(["".join(item) for item in history] + [query])
+            history = []
+        return query.strip(), resp, history
+
+
+eval_templates: Dict[str, EvalTemplate] = {}
+
+
+def register_eval_template(
+    name: str,
+    system: str,
+    choice: str,
+    answer: str,
+    prefix: str
+) -> None:
+    eval_templates[name] = EvalTemplate(
+        system=system,
+        choice=choice,
+        answer=answer,
+        prefix=prefix
+    )
+
+
+def get_eval_template(name: str) -> EvalTemplate:
+    eval_template = eval_templates.get(name, None)
+    assert eval_template is not None, "Template {} does not exist.".format(name)
+    return eval_template
+
+
+register_eval_template(
+    name="en",
+    system="The following are multiple choice questions (with answers) about {subject}.\n\n",
+    choice="\n{choice}. {content}",
+    answer="\nAnswer: ",
+    prefix=" "
+)
+
+
+register_eval_template(
+    name="zh",
+    system="以下是中国关于{subject}考试的单项选择题，请选出其中的正确答案。\n\n",
+    choice="\n{choice}. {content}",
+    answer="\n答案：",
+    prefix="\n"
+)

LLM-Detector-V7-11w/src/llmtuner/extras/callbacks.py

@@ -0,0 +1,148 @@
+import os
+import json
+import time
+from typing import TYPE_CHECKING
+from datetime import timedelta
+from transformers import TrainerCallback
+from transformers.trainer_utils import has_length, PREFIX_CHECKPOINT_DIR
+
+from llmtuner.extras.constants import LOG_FILE_NAME
+from llmtuner.extras.logging import get_logger
+from llmtuner.extras.misc import fix_valuehead_checkpoint
+
+
+if TYPE_CHECKING:
+    from transformers import TrainingArguments, TrainerState, TrainerControl
+
+
+logger = get_logger(__name__)
+
+
+class FixValueHeadModelCallback(TrainerCallback):
+
+    def on_save(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs):
+        r"""
+        Event called after a checkpoint save.
+        """
+        if args.should_save:
+            fix_valuehead_checkpoint(
+                model=kwargs.pop("model"),
+                output_dir=os.path.join(args.output_dir, "{}-{}".format(PREFIX_CHECKPOINT_DIR, state.global_step)),
+                safe_serialization=args.save_safetensors
+            )
+
+
+class LogCallback(TrainerCallback):
+
+    def __init__(self, runner=None):
+        self.runner = runner
+        self.in_training = False
+        self.start_time = time.time()
+        self.cur_steps = 0
+        self.max_steps = 0
+        self.elapsed_time = ""
+        self.remaining_time = ""
+
+    def timing(self):
+        cur_time = time.time()
+        elapsed_time = cur_time - self.start_time
+        avg_time_per_step = elapsed_time / self.cur_steps if self.cur_steps != 0 else 0
+        remaining_time = (self.max_steps - self.cur_steps) * avg_time_per_step
+        self.elapsed_time = str(timedelta(seconds=int(elapsed_time)))
+        self.remaining_time = str(timedelta(seconds=int(remaining_time)))
+
+    def on_train_begin(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs):
+        r"""
+        Event called at the beginning of training.
+        """
+        if state.is_local_process_zero:
+            self.in_training = True
+            self.start_time = time.time()
+            self.max_steps = state.max_steps
+            if os.path.exists(os.path.join(args.output_dir, LOG_FILE_NAME)) and args.overwrite_output_dir:
+                logger.warning("Previous log file in this folder will be deleted.")
+                os.remove(os.path.join(args.output_dir, LOG_FILE_NAME))
+
+    def on_train_end(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs):
+        r"""
+        Event called at the end of training.
+        """
+        if state.is_local_process_zero:
+            self.in_training = False
+            self.cur_steps = 0
+            self.max_steps = 0
+
+    def on_substep_end(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs):
+        r"""
+        Event called at the end of an substep during gradient accumulation.
+        """
+        if state.is_local_process_zero and self.runner is not None and self.runner.aborted:
+            control.should_epoch_stop = True
+            control.should_training_stop = True
+
+    def on_step_end(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs):
+        r"""
+        Event called at the end of a training step.
+        """
+        if state.is_local_process_zero:
+            self.cur_steps = state.global_step
+            self.timing()
+            if self.runner is not None and self.runner.aborted:
+                control.should_epoch_stop = True
+                control.should_training_stop = True
+
+    def on_evaluate(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs):
+        r"""
+        Event called after an evaluation phase.
+        """
+        if state.is_local_process_zero and not self.in_training:
+            self.cur_steps = 0
+            self.max_steps = 0
+
+    def on_predict(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", *other, **kwargs):
+        r"""
+        Event called after a successful prediction.
+        """
+        if state.is_local_process_zero and not self.in_training:
+            self.cur_steps = 0
+            self.max_steps = 0
+
+    def on_log(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs) -> None:
+        r"""
+        Event called after logging the last logs.
+        """
+        if not state.is_local_process_zero:
+            return
+
+        logs = dict(
+            current_steps=self.cur_steps,
+            total_steps=self.max_steps,
+            loss=state.log_history[-1].get("loss", None),
+            eval_loss=state.log_history[-1].get("eval_loss", None),
+            predict_loss=state.log_history[-1].get("predict_loss", None),
+            reward=state.log_history[-1].get("reward", None),
+            learning_rate=state.log_history[-1].get("learning_rate", None),
+            epoch=state.log_history[-1].get("epoch", None),
+            percentage=round(self.cur_steps / self.max_steps * 100, 2) if self.max_steps != 0 else 100,
+            elapsed_time=self.elapsed_time,
+            remaining_time=self.remaining_time
+        )
+        if self.runner is not None:
+            logger.info("{{'loss': {:.4f}, 'learning_rate': {:2.4e}, 'epoch': {:.2f}}}".format(
+                logs["loss"] or 0, logs["learning_rate"] or 0, logs["epoch"] or 0
+            ))
+
+        os.makedirs(args.output_dir, exist_ok=True)
+        with open(os.path.join(args.output_dir, "trainer_log.jsonl"), "a", encoding="utf-8") as f:
+            f.write(json.dumps(logs) + "\n")
+
+    def on_prediction_step(self, args: "TrainingArguments", state: "TrainerState", control: "TrainerControl", **kwargs):
+        r"""
+        Event called after a prediction step.
+        """
+        eval_dataloader = kwargs.pop("eval_dataloader", None)
+        if state.is_local_process_zero and has_length(eval_dataloader) and not self.in_training:
+            if self.max_steps == 0:
+                self.max_steps = len(eval_dataloader)
+            self.cur_steps += 1
+            self.timing()

LLM-Detector-V7-11w/src/llmtuner/extras/constants.py

@@ -0,0 +1,707 @@
+from enum import Enum
+from collections import defaultdict, OrderedDict
+from typing import Dict, Optional
+
+
+CHOICES = ["A", "B", "C", "D"]
+
+DEFAULT_MODULE = defaultdict(str)
+
+DEFAULT_TEMPLATE = defaultdict(str)
+
+FILEEXT2TYPE = {
+    "arrow": "arrow",
+    "csv": "csv",
+    "json": "json",
+    "jsonl": "json",
+    "parquet": "parquet",
+    "txt": "text"
+}
+
+IGNORE_INDEX = -100
+
+LAYERNORM_NAMES = {"norm", "ln"}
+
+LOG_FILE_NAME = "trainer_log.jsonl"
+
+METHODS = ["full", "freeze", "lora"]
+
+PEFT_METHODS = ["lora"]
+
+SUBJECTS = ["Average", "STEM", "Social Sciences", "Humanities", "Other"]
+
+SUPPORTED_MODELS = OrderedDict()
+
+TRAINING_STAGES = {
+    "Supervised Fine-Tuning": "sft",
+    "Reward Modeling": "rm",
+    "PPO": "ppo",
+    "DPO": "dpo",
+    "Pre-Training": "pt"
+}
+
+V_HEAD_WEIGHTS_NAME = "value_head.bin"
+
+V_HEAD_SAFE_WEIGHTS_NAME = "value_head.safetensors"
+
+class DownloadSource(str, Enum):
+    DEFAULT = "hf"
+    MODELSCOPE = "ms"
+
+
+def register_model_group(
+    models: Dict[str, Dict[DownloadSource, str]],
+    module: Optional[str] = None,
+    template: Optional[str] = None
+) -> None:
+    prefix = None
+    for name, path in models.items():
+        if prefix is None:
+            prefix = name.split("-")[0]
+        else:
+            assert prefix == name.split("-")[0], "prefix should be identical."
+        SUPPORTED_MODELS[name] = path
+    if module is not None:
+        DEFAULT_MODULE[prefix] = module
+    if template is not None:
+        DEFAULT_TEMPLATE[prefix] = template
+
+
+register_model_group(
+    models={
+        "Baichuan-7B-Base": {
+            DownloadSource.DEFAULT: "baichuan-inc/Baichuan-7B",
+            DownloadSource.MODELSCOPE: "baichuan-inc/baichuan-7B"
+        },
+        "Baichuan-13B-Base": {
+            DownloadSource.DEFAULT: "baichuan-inc/Baichuan-13B-Base",
+            DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan-13B-Base"
+        },
+        "Baichuan-13B-Chat": {
+            DownloadSource.DEFAULT: "baichuan-inc/Baichuan-13B-Chat",
+            DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan-13B-Chat"
+        }
+    },
+    module="W_pack",
+    template="baichuan"
+)
+
+
+register_model_group(
+    models={
+        "Baichuan2-7B-Base": {
+            DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-7B-Base",
+            DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-7B-Base"
+        },
+        "Baichuan2-13B-Base": {
+            DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-13B-Base",
+            DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-13B-Base"
+        },
+        "Baichuan2-7B-Chat": {
+            DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-7B-Chat",
+            DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-7B-Chat"
+        },
+        "Baichuan2-13B-Chat": {
+            DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-13B-Chat",
+            DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-13B-Chat"
+        }
+    },
+    module="W_pack",
+    template="baichuan2"
+)
+
+
+register_model_group(
+    models={
+        "BLOOM-560M": {
+            DownloadSource.DEFAULT: "bigscience/bloom-560m",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/bloom-560m"
+        },
+        "BLOOM-3B": {
+            DownloadSource.DEFAULT: "bigscience/bloom-3b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/bloom-3b"
+        },
+        "BLOOM-7B1": {
+            DownloadSource.DEFAULT: "bigscience/bloom-7b1",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/bloom-7b1"
+        }
+    },
+    module="query_key_value"
+)
+
+
+register_model_group(
+    models={
+        "BLOOMZ-560M": {
+            DownloadSource.DEFAULT: "bigscience/bloomz-560m",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/bloomz-560m"
+        },
+        "BLOOMZ-3B": {
+            DownloadSource.DEFAULT: "bigscience/bloomz-3b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/bloomz-3b"
+        },
+        "BLOOMZ-7B1-mt": {
+            DownloadSource.DEFAULT: "bigscience/bloomz-7b1-mt",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/bloomz-7b1-mt"
+        }
+    },
+    module="query_key_value"
+)
+
+
+register_model_group(
+    models={
+        "BlueLM-7B-Base": {
+            DownloadSource.DEFAULT: "vivo-ai/BlueLM-7B-Base",
+            DownloadSource.MODELSCOPE: "vivo-ai/BlueLM-7B-Base"
+        },
+        "BlueLM-7B-Chat": {
+            DownloadSource.DEFAULT: "vivo-ai/BlueLM-7B-Chat",
+            DownloadSource.MODELSCOPE: "vivo-ai/BlueLM-7B-Chat"
+        }
+    },
+    template="bluelm"
+)
+
+
+register_model_group(
+    models={
+        "ChatGLM2-6B-Chat": {
+            DownloadSource.DEFAULT: "THUDM/chatglm2-6b",
+            DownloadSource.MODELSCOPE: "ZhipuAI/chatglm2-6b"
+        }
+    },
+    module="query_key_value",
+    template="chatglm2"
+)
+
+
+register_model_group(
+    models={
+        "ChatGLM3-6B-Base": {
+            DownloadSource.DEFAULT: "THUDM/chatglm3-6b-base",
+            DownloadSource.MODELSCOPE: "ZhipuAI/chatglm3-6b-base"
+        },
+        "ChatGLM3-6B-Chat": {
+            DownloadSource.DEFAULT: "THUDM/chatglm3-6b",
+            DownloadSource.MODELSCOPE: "ZhipuAI/chatglm3-6b"
+        }
+    },
+    module="query_key_value",
+    template="chatglm3"
+)
+
+
+register_model_group(
+    models={
+        "ChineseLLaMA2-1.3B": {
+            DownloadSource.DEFAULT: "hfl/chinese-llama-2-1.3b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-llama-2-1.3b"
+        },
+        "ChineseLLaMA2-7B": {
+            DownloadSource.DEFAULT: "hfl/chinese-llama-2-7b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-llama-2-7b"
+        },
+        "ChineseLLaMA2-13B": {
+            DownloadSource.DEFAULT: "hfl/chinese-llama-2-13b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-llama-2-13b"
+        },
+        "ChineseLLaMA2-1.3B-Chat": {
+            DownloadSource.DEFAULT: "hfl/chinese-alpaca-2-1.3b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-alpaca-2-1.3b"
+        },
+        "ChineseLLaMA2-7B-Chat": {
+            DownloadSource.DEFAULT: "hfl/chinese-alpaca-2-7b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-alpaca-2-7b"
+        },
+        "ChineseLLaMA2-13B-Chat": {
+            DownloadSource.DEFAULT: "hfl/chinese-alpaca-2-13b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-alpaca-2-13b"
+        }
+    },
+    template="llama2_zh"
+)
+
+
+register_model_group(
+    models={
+        "DeepseekLLM-7B-Base": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-base",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-base"
+        },
+        "DeepseekLLM-67B-Base": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-base",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-base"
+        },
+        "DeepseekLLM-7B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-chat",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-chat"
+        },
+        "DeepseekLLM-67B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-chat",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-chat"
+        }
+    },
+    template="deepseek"
+)
+
+
+register_model_group(
+    models={
+        "DeepseekCoder-6.7B-Base": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-6.7b-base",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-6.7b-base"
+        },
+        "DeepseekCoder-33B-Base": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-base",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-33b-base"
+        },
+        "DeepseekCoder-6.7B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-6.7b-instruct",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-6.7b-instruct"
+        },
+        "DeepseekCoder-33B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-instruct",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-33b-instruct"
+        }
+    },
+    template="deepseekcoder"
+)
+
+
+register_model_group(
+    models={
+        "DeepseekMoE-16B-Base": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base"
+        },
+        "DeepseekMoE-16B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat"
+        }
+    },
+    template="deepseek"
+)
+
+
+register_model_group(
+    models={
+        "Falcon-7B": {
+            DownloadSource.DEFAULT: "tiiuae/falcon-7b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/falcon-7b"
+        },
+        "Falcon-40B": {
+            DownloadSource.DEFAULT: "tiiuae/falcon-40b",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/falcon-40b"
+        },
+        "Falcon-180B": {
+            DownloadSource.DEFAULT: "tiiuae/falcon-180b",
+            DownloadSource.MODELSCOPE: "modelscope/falcon-180B"
+        },
+        "Falcon-7B-Chat": {
+            DownloadSource.DEFAULT: "tiiuae/falcon-7b-instruct",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/falcon-7b-instruct"
+        },
+        "Falcon-40B-Chat": {
+            DownloadSource.DEFAULT: "tiiuae/falcon-40b-instruct",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/falcon-40b-instruct"
+        },
+        "Falcon-180B-Chat": {
+            DownloadSource.DEFAULT: "tiiuae/falcon-180b-chat",
+            DownloadSource.MODELSCOPE: "modelscope/falcon-180B-chat"
+        }
+    },
+    module="query_key_value",
+    template="falcon"
+)
+
+
+register_model_group(
+    models={
+        "InternLM-7B": {
+            DownloadSource.DEFAULT: "internlm/internlm-7b",
+            DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm-7b"
+        },
+        "InternLM-20B": {
+            DownloadSource.DEFAULT: "internlm/internlm-20b",
+            DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm-20b"
+        },
+        "InternLM-7B-Chat": {
+            DownloadSource.DEFAULT: "internlm/internlm-chat-7b",
+            DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm-chat-7b"
+        },
+        "InternLM-20B-Chat": {
+            DownloadSource.DEFAULT: "internlm/internlm-chat-20b",
+            DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm-chat-20b"
+        }
+    },
+    template="intern"
+)
+
+
+register_model_group(
+    models={
+        "LingoWhale-8B": {
+            DownloadSource.DEFAULT: "deeplang-ai/LingoWhale-8B",
+            DownloadSource.MODELSCOPE: "DeepLang/LingoWhale-8B"
+        }
+    },
+    module="qkv_proj"
+)
+
+
+register_model_group(
+    models={
+        "LLaMA-7B": {
+            DownloadSource.DEFAULT: "huggyllama/llama-7b",
+            DownloadSource.MODELSCOPE: "skyline2006/llama-7b"
+        },
+        "LLaMA-13B": {
+            DownloadSource.DEFAULT: "huggyllama/llama-13b",
+            DownloadSource.MODELSCOPE: "skyline2006/llama-13b"
+        },
+        "LLaMA-30B": {
+            DownloadSource.DEFAULT: "huggyllama/llama-30b",
+            DownloadSource.MODELSCOPE: "skyline2006/llama-30b"
+        },
+        "LLaMA-65B": {
+            DownloadSource.DEFAULT: "huggyllama/llama-65b",
+            DownloadSource.MODELSCOPE: "skyline2006/llama-65b"
+        }
+    }
+)
+
+
+register_model_group(
+    models={
+        "LLaMA2-7B": {
+            DownloadSource.DEFAULT: "meta-llama/Llama-2-7b-hf",
+            DownloadSource.MODELSCOPE: "modelscope/Llama-2-7b-ms"
+        },
+        "LLaMA2-13B": {
+            DownloadSource.DEFAULT: "meta-llama/Llama-2-13b-hf",
+            DownloadSource.MODELSCOPE: "modelscope/Llama-2-13b-ms"
+        },
+        "LLaMA2-70B": {
+            DownloadSource.DEFAULT: "meta-llama/Llama-2-70b-hf",
+            DownloadSource.MODELSCOPE: "modelscope/Llama-2-70b-ms"
+        },
+        "LLaMA2-7B-Chat": {
+            DownloadSource.DEFAULT: "meta-llama/Llama-2-7b-chat-hf",
+            DownloadSource.MODELSCOPE: "modelscope/Llama-2-7b-chat-ms"
+        },
+        "LLaMA2-13B-Chat": {
+            DownloadSource.DEFAULT: "meta-llama/Llama-2-13b-chat-hf",
+            DownloadSource.MODELSCOPE: "modelscope/Llama-2-13b-chat-ms"
+        },
+        "LLaMA2-70B-Chat": {
+            DownloadSource.DEFAULT: "meta-llama/Llama-2-70b-chat-hf",
+            DownloadSource.MODELSCOPE: "modelscope/Llama-2-70b-chat-ms"
+        }
+    },
+    template="llama2"
+)
+
+
+register_model_group(
+    models={
+        "Mistral-7B": {
+            DownloadSource.DEFAULT: "mistralai/Mistral-7B-v0.1",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-v0.1"
+        },
+        "Mistral-7B-Chat": {
+            DownloadSource.DEFAULT: "mistralai/Mistral-7B-Instruct-v0.1",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-Instruct-v0.1"
+        },
+        "Mistral-7B-v0.2-Chat": {
+            DownloadSource.DEFAULT: "mistralai/Mistral-7B-Instruct-v0.2",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-Instruct-v0.2"
+        }
+    },
+    template="mistral"
+)
+
+
+register_model_group(
+    models={
+        "Mixtral-8x7B": {
+            DownloadSource.DEFAULT: "mistralai/Mixtral-8x7B-v0.1",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/Mixtral-8x7B-v0.1"
+        },
+        "Mixtral-8x7B-Chat": {
+            DownloadSource.DEFAULT: "mistralai/Mixtral-8x7B-Instruct-v0.1",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/Mixtral-8x7B-Instruct-v0.1"
+        }
+    },
+    template="mistral"
+)
+
+
+register_model_group(
+    models={
+        "OpenChat3.5-7B-Chat": {
+            DownloadSource.DEFAULT: "openchat/openchat_3.5",
+            DownloadSource.MODELSCOPE: "myxiongmodel/openchat_3.5"
+        }
+    },
+    template="openchat"
+)
+
+
+register_model_group(
+    models={
+        "Phi-1.5-1.3B": {
+            DownloadSource.DEFAULT: "microsoft/phi-1_5",
+            DownloadSource.MODELSCOPE: "allspace/PHI_1-5"
+        },
+        "Phi-2-2.7B": {
+            DownloadSource.DEFAULT: "microsoft/phi-2",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/phi-2"
+        }
+    }
+)
+
+
+register_model_group(
+    models={
+        "Qwen-1.8B": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-1_8B",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-1_8B"
+        },
+        "Qwen-7B": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-7B",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-7B"
+        },
+        "Qwen-14B": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-14B",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-14B"
+        },
+        "Qwen-72B": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-72B",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-72B"
+        },
+        "Qwen-1.8B-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-1_8B-Chat",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-1_8B-Chat"
+        },
+        "Qwen-7B-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-7B-Chat",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-7B-Chat"
+        },
+        "Qwen-14B-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-14B-Chat",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-14B-Chat"
+        },
+        "Qwen-72B-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-72B-Chat",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-72B-Chat"
+        },
+        "Qwen-1.8B-int8-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-1_8B-Chat-Int8",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-1_8B-Chat-Int8"
+        },
+        "Qwen-1.8B-int4-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-1_8B-Chat-Int4",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-1_8B-Chat-Int4"
+        },
+        "Qwen-7B-int8-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-7B-Chat-Int8",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-7B-Chat-Int8"
+        },
+        "Qwen-7B-int4-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-7B-Chat-Int4",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-7B-Chat-Int4"
+        },
+        "Qwen-14B-int8-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-14B-Chat-Int8",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-14B-Chat-Int8"
+        },
+        "Qwen-14B-int4-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-14B-Chat-Int4",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-14B-Chat-Int4"
+        },
+        "Qwen-72B-int8-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-72B-Chat-Int8",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-72B-Chat-Int8"
+        },
+        "Qwen-72B-int4-Chat": {
+            DownloadSource.DEFAULT: "Qwen/Qwen-72B-Chat-Int4",
+            DownloadSource.MODELSCOPE: "qwen/Qwen-72B-Chat-Int4"
+        }
+    },
+    module="c_attn",
+    template="qwen"
+)
+
+
+register_model_group(
+    models={
+        "SOLAR-10.7B": {
+            DownloadSource.DEFAULT: "upstage/SOLAR-10.7B-v1.0"
+        },
+        "SOLAR-10.7B-Chat": {
+            DownloadSource.DEFAULT: "upstage/SOLAR-10.7B-Instruct-v1.0",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/SOLAR-10.7B-Instruct-v1.0"
+        }
+    },
+    template="solar"
+)
+
+
+register_model_group(
+    models={
+        "Skywork-13B-Base": {
+            DownloadSource.DEFAULT: "Skywork/Skywork-13B-base",
+            DownloadSource.MODELSCOPE: "skywork/Skywork-13B-base"
+        }
+    }
+)
+
+
+register_model_group(
+    models={
+        "Vicuna1.5-7B-Chat": {
+            DownloadSource.DEFAULT: "lmsys/vicuna-7b-v1.5",
+            DownloadSource.MODELSCOPE: "Xorbits/vicuna-7b-v1.5"
+        },
+        "Vicuna1.5-13B-Chat": {
+            DownloadSource.DEFAULT: "lmsys/vicuna-13b-v1.5",
+            DownloadSource.MODELSCOPE: "Xorbits/vicuna-13b-v1.5"
+        }
+    },
+    template="vicuna"
+)
+
+
+register_model_group(
+    models={
+        "XuanYuan-70B": {
+            DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B"
+        },
+        "XuanYuan-70B-Chat": {
+            DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B-Chat"
+        },
+        "XuanYuan-70B-int8-Chat": {
+            DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B-Chat-8bit"
+        },
+        "XuanYuan-70B-int4-Chat": {
+            DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B-Chat-4bit"
+        }
+    },
+    template="xuanyuan"
+)
+
+
+register_model_group(
+    models={
+        "XVERSE-7B": {
+            DownloadSource.DEFAULT: "xverse/XVERSE-7B",
+            DownloadSource.MODELSCOPE: "xverse/XVERSE-7B"
+        },
+        "XVERSE-13B": {
+            DownloadSource.DEFAULT: "xverse/XVERSE-13B",
+            DownloadSource.MODELSCOPE: "xverse/XVERSE-13B"
+        },
+        "XVERSE-65B": {
+            DownloadSource.DEFAULT: "xverse/XVERSE-65B",
+            DownloadSource.MODELSCOPE: "xverse/XVERSE-65B"
+        },
+        "XVERSE-65B-2": {
+            DownloadSource.DEFAULT: "xverse/XVERSE-65B-2",
+            DownloadSource.MODELSCOPE: "xverse/XVERSE-65B-2"
+        },
+        "XVERSE-7B-Chat": {
+            DownloadSource.DEFAULT: "xverse/XVERSE-7B-Chat",
+            DownloadSource.MODELSCOPE: "xverse/XVERSE-7B-Chat"
+        },
+        "XVERSE-13B-Chat": {
+            DownloadSource.DEFAULT: "xverse/XVERSE-13B-Chat",
+            DownloadSource.MODELSCOPE: "xverse/XVERSE-13B-Chat"
+        },
+        "XVERSE-65B-Chat": {
+            DownloadSource.DEFAULT: "xverse/XVERSE-65B-Chat",
+            DownloadSource.MODELSCOPE: "xverse/XVERSE-65B-Chat"
+        }
+    },
+    template="xverse"
+)
+
+
+register_model_group(
+    models={
+        "Yayi-7B": {
+            DownloadSource.DEFAULT: "wenge-research/yayi-7b-llama2",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/yayi-7b-llama2"
+        },
+        "Yayi-13B": {
+            DownloadSource.DEFAULT: "wenge-research/yayi-13b-llama2",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/yayi-13b-llama2"
+        }
+    },
+    template="yayi"
+)
+
+
+register_model_group(
+    models={
+        "Yi-6B": {
+            DownloadSource.DEFAULT: "01-ai/Yi-6B",
+            DownloadSource.MODELSCOPE: "01ai/Yi-6B"
+        },
+        "Yi-34B": {
+            DownloadSource.DEFAULT: "01-ai/Yi-34B",
+            DownloadSource.MODELSCOPE: "01ai/Yi-34B"
+        },
+        "Yi-6B-Chat": {
+            DownloadSource.DEFAULT: "01-ai/Yi-6B-Chat",
+            DownloadSource.MODELSCOPE: "01ai/Yi-6B-Chat"
+        },
+        "Yi-34B-Chat": {
+            DownloadSource.DEFAULT: "01-ai/Yi-34B-Chat",
+            DownloadSource.MODELSCOPE: "01ai/Yi-34B-Chat"
+        },
+        "Yi-6B-int8-Chat": {
+            DownloadSource.DEFAULT: "01-ai/Yi-6B-Chat-8bits",
+            DownloadSource.MODELSCOPE: "01ai/Yi-6B-Chat-8bits"
+        },
+        "Yi-34B-int8-Chat": {
+            DownloadSource.DEFAULT: "01-ai/Yi-34B-Chat-8bits",
+            DownloadSource.MODELSCOPE: "01ai/Yi-34B-Chat-8bits"
+        }
+    },
+    template="yi"
+)
+
+
+register_model_group(
+    models={
+        "Yuan2-2B-Chat": {
+            DownloadSource.DEFAULT: "IEITYuan/Yuan2-2B-hf",
+            DownloadSource.MODELSCOPE: "YuanLLM/Yuan2.0-2B-hf"
+        },
+        "Yuan2-51B-Chat": {
+            DownloadSource.DEFAULT: "IEITYuan/Yuan2-51B-hf",
+            DownloadSource.MODELSCOPE: "YuanLLM/Yuan2.0-51B-hf"
+        },
+        "Yuan2-102B-Chat": {
+            DownloadSource.DEFAULT: "IEITYuan/Yuan2-102B-hf",
+            DownloadSource.MODELSCOPE: "YuanLLM/Yuan2.0-102B-hf"
+        }
+    },
+    template="yuan"
+)
+
+
+register_model_group(
+    models={
+        "Zephyr-7B-Alpha-Chat": {
+            DownloadSource.DEFAULT: "HuggingFaceH4/zephyr-7b-alpha",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/zephyr-7b-alpha"
+        },
+        "Zephyr-7B-Beta-Chat": {
+            DownloadSource.DEFAULT: "HuggingFaceH4/zephyr-7b-beta",
+            DownloadSource.MODELSCOPE: "modelscope/zephyr-7b-beta"
+        }
+    },
+    template="zephyr"
+)

LLM-Detector-V7-11w/src/llmtuner/extras/logging.py

@@ -0,0 +1,49 @@
+import sys
+import logging
+
+
+class LoggerHandler(logging.Handler):
+    r"""
+    Logger handler used in Web UI.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.log = ""
+
+    def reset(self):
+        self.log = ""
+
+    def emit(self, record):
+        if record.name == "httpx":
+            return
+        log_entry = self.format(record)
+        self.log += log_entry
+        self.log += "\n\n"
+
+
+def get_logger(name: str) -> logging.Logger:
+    r"""
+    Gets a standard logger with a stream hander to stdout.
+    """
+    formatter = logging.Formatter(
+        fmt="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S"
+    )
+    handler = logging.StreamHandler(sys.stdout)
+    handler.setFormatter(formatter)
+
+    logger = logging.getLogger(name)
+    logger.setLevel(logging.INFO)
+    logger.addHandler(handler)
+
+    return logger
+
+
+def reset_logging() -> None:
+    r"""
+    Removes basic config of root logger. (unused in script)
+    """
+    root = logging.getLogger()
+    list(map(root.removeHandler, root.handlers))
+    list(map(root.removeFilter, root.filters))

LLM-Detector-V7-11w/src/llmtuner/extras/misc.py

@@ -0,0 +1,196 @@
+import gc
+import os
+import torch
+from typing import TYPE_CHECKING, Dict, Tuple
+from transformers import InfNanRemoveLogitsProcessor, LogitsProcessorList, PreTrainedModel
+from transformers.utils import (
+    WEIGHTS_NAME,
+    SAFE_WEIGHTS_NAME,
+    is_torch_bf16_gpu_available,
+    is_torch_cuda_available,
+    is_torch_npu_available,
+    is_torch_xpu_available
+)
+from peft import PeftModel
+
+from llmtuner.extras.constants import V_HEAD_WEIGHTS_NAME, V_HEAD_SAFE_WEIGHTS_NAME
+from llmtuner.extras.logging import get_logger
+
+
+_is_fp16_available = is_torch_npu_available() or is_torch_cuda_available()
+try:
+    _is_bf16_available = is_torch_bf16_gpu_available()
+except:
+    _is_bf16_available = False
+
+
+if TYPE_CHECKING:
+    from trl import AutoModelForCausalLMWithValueHead
+    from llmtuner.hparams import ModelArguments
+
+
+logger = get_logger(__name__)
+
+
+class AverageMeter:
+    r"""
+    Computes and stores the average and current value.
+    """
+    def __init__(self):
+        self.reset()
+
+    def reset(self):
+        self.val = 0
+        self.avg = 0
+        self.sum = 0
+        self.count = 0
+
+    def update(self, val, n=1):
+        self.val = val
+        self.sum += val * n
+        self.count += n
+        self.avg = self.sum / self.count
+
+
+def count_parameters(model: torch.nn.Module) -> Tuple[int, int]:
+    r"""
+    Returns the number of trainable parameters and number of all parameters in the model.
+    """
+    trainable_params, all_param = 0, 0
+    for param in model.parameters():
+        num_params = param.numel()
+        # if using DS Zero 3 and the weights are initialized empty
+        if num_params == 0 and hasattr(param, "ds_numel"):
+            num_params = param.ds_numel
+
+        # Due to the design of 4bit linear layers from bitsandbytes, multiply the number of parameters by 2
+        if param.__class__.__name__ == "Params4bit":
+            num_params = num_params * 2
+
+        all_param += num_params
+        if param.requires_grad:
+            trainable_params += num_params
+
+    return trainable_params, all_param
+
+
+def fix_valuehead_checkpoint(
+    model: "AutoModelForCausalLMWithValueHead",
+    output_dir: str,
+    safe_serialization: bool
+) -> None:
+    r"""
+    The model is already unwrapped.
+
+    There are three cases:
+    1. full tuning without ds_zero3: state_dict = {"model.layers.*": ..., "v_head.summary.*": ...}
+    2. lora tuning without ds_zero3: state_dict = {"v_head.summary.*": ...}
+    3. under deepspeed zero3: state_dict = {"pretrained_model.model.layers.*": ..., "v_head.summary.*": ...}
+
+    We assume `stage3_gather_16bit_weights_on_model_save=true`.
+    """
+    if not isinstance(model.pretrained_model, (PreTrainedModel, PeftModel)):
+        return
+
+    if safe_serialization:
+        from safetensors import safe_open
+        from safetensors.torch import save_file
+        path_to_checkpoint = os.path.join(output_dir, SAFE_WEIGHTS_NAME)
+        with safe_open(path_to_checkpoint, framework="pt", device="cpu") as f:
+            state_dict: Dict[str, torch.Tensor] = {key: f.get_tensor(key) for key in f.keys()}
+    else:
+        path_to_checkpoint = os.path.join(output_dir, WEIGHTS_NAME)
+        state_dict: Dict[str, torch.Tensor] = torch.load(path_to_checkpoint, map_location="cpu")
+
+    decoder_state_dict = {}
+    v_head_state_dict = {}
+    for name, param in state_dict.items():
+        if name.startswith("v_head."):
+            v_head_state_dict[name] = param
+        else:
+            decoder_state_dict[name.replace("pretrained_model.", "")] = param
+
+    os.remove(path_to_checkpoint)
+    model.pretrained_model.save_pretrained(
+        output_dir,
+        state_dict=decoder_state_dict or None,
+        safe_serialization=safe_serialization
+    )
+
+    if safe_serialization:
+        save_file(v_head_state_dict, os.path.join(output_dir, V_HEAD_SAFE_WEIGHTS_NAME), metadata={"format": "pt"})
+    else:
+        torch.save(v_head_state_dict, os.path.join(output_dir, V_HEAD_WEIGHTS_NAME))
+
+    logger.info("Value head model saved at: {}".format(output_dir))
+
+
+def get_current_device() -> torch.device:
+    r"""
+    Gets the current available device.
+    """
+    if is_torch_xpu_available():
+        device = "xpu:{}".format(os.environ.get("LOCAL_RANK", "0"))
+    elif is_torch_npu_available():
+        device = "npu:{}".format(os.environ.get("LOCAL_RANK", "0"))
+    elif is_torch_cuda_available():
+        device = "cuda:{}".format(os.environ.get("LOCAL_RANK", "0"))
+    else:
+        device = "cpu"
+
+    return torch.device(device)
+
+
+def get_device_count() -> int:
+    return torch.cuda.device_count()
+
+
+def get_logits_processor() -> "LogitsProcessorList":
+    r"""
+    Gets logits processor that removes NaN and Inf logits.
+    """
+    logits_processor = LogitsProcessorList()
+    logits_processor.append(InfNanRemoveLogitsProcessor())
+    return logits_processor
+
+
+def infer_optim_dtype(model_dtype: torch.dtype) -> torch.dtype:
+    r"""
+    Infers the optimal dtype according to the model_dtype and device compatibility.
+    """
+    if _is_bf16_available and model_dtype == torch.bfloat16:
+        return torch.bfloat16
+    elif _is_fp16_available:
+        return torch.float16
+    else:
+        return torch.float32
+
+
+def torch_gc() -> None:
+    r"""
+    Collects GPU memory.
+    """
+    gc.collect()
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+        torch.cuda.ipc_collect()
+
+
+def try_download_model_from_ms(model_args: "ModelArguments") -> None:
+    if not use_modelscope() or os.path.exists(model_args.model_name_or_path):
+        return
+
+    try:
+        from modelscope import snapshot_download
+        revision = "master" if model_args.model_revision == "main" else model_args.model_revision
+        model_args.model_name_or_path = snapshot_download(
+            model_args.model_name_or_path,
+            revision=revision,
+            cache_dir=model_args.cache_dir
+        )
+    except ImportError:
+        raise ImportError("Please install modelscope via `pip install modelscope -U`")
+
+
+def use_modelscope() -> bool:
+    return bool(int(os.environ.get("USE_MODELSCOPE_HUB", "0")))

LLM-Detector-V7-11w/src/llmtuner/extras/packages.py

@@ -0,0 +1,49 @@
+import importlib.metadata
+import importlib.util
+
+
+def is_package_available(name: str) -> bool:
+    return importlib.util.find_spec(name) is not None
+
+
+def get_package_version(name: str) -> str:
+    try:
+        return importlib.metadata.version(name)
+    except:
+        return "0.0.0"
+
+
+def is_fastapi_availble():
+    return is_package_available("fastapi")
+
+
+def is_flash_attn2_available():
+    return is_package_available("flash_attn") and get_package_version("flash_attn").startswith("2")
+
+
+def is_jieba_available():
+    return is_package_available("jieba")
+
+
+def is_matplotlib_available():
+    return is_package_available("matplotlib")
+
+
+def is_nltk_available():
+    return is_package_available("nltk")
+
+
+def is_requests_available():
+    return is_package_available("requests")
+
+
+def is_rouge_available():
+    return is_package_available("rouge_chinese")
+
+
+def is_starlette_available():
+    return is_package_available("sse_starlette")
+
+
+def is_uvicorn_available():
+    return is_package_available("uvicorn")

LLM-Detector-V7-11w/src/llmtuner/extras/patches/llama_patch.py

@@ -0,0 +1,224 @@
+import math
+import torch
+import torch.nn as nn
+from typing import Optional, Tuple
+from transformers.utils import logging
+from transformers.models.llama.modeling_llama import LlamaAttention, apply_rotary_pos_emb
+
+try:
+    from transformers.models.llama.modeling_llama import repeat_kv
+except ImportError:
+    print("Please upgrade `transformers`.")
+
+from llmtuner.extras.packages import is_flash_attn2_available
+
+
+if is_flash_attn2_available():
+    from flash_attn import flash_attn_func, flash_attn_varlen_func # type: ignore
+    from flash_attn.bert_padding import pad_input, unpad_input # type: ignore
+
+
+logger = logging.get_logger(__name__)
+
+
+# Modified from: https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py
+class LlamaShiftShortAttention(LlamaAttention):
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_value: Optional[Tuple[torch.Tensor]] = None,
+        output_attentions: bool = False,
+        use_cache: bool = False,
+        **kwargs
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
+        bsz, q_len, _ = hidden_states.size()
+
+        query_states = self.q_proj(hidden_states)
+        key_states = self.k_proj(hidden_states)
+        value_states = self.v_proj(hidden_states)
+
+        query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
+        key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+        value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+
+        kv_seq_len = key_states.shape[-2]
+        if past_key_value is not None:
+            kv_seq_len += past_key_value[0].shape[-2]
+
+        cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
+        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
+
+        if past_key_value is not None: # reuse k, v, self_attention
+            key_states = torch.cat([past_key_value[0], key_states], dim=2)
+            value_states = torch.cat([past_key_value[1], value_states], dim=2)
+
+        past_key_value = (key_states, value_states) if use_cache else None
+
+        if getattr(self, "num_key_value_groups"):
+            key_states = repeat_kv(key_states, self.num_key_value_groups)
+            value_states = repeat_kv(value_states, self.num_key_value_groups)
+
+        if getattr(self.config, "group_size_ratio", None) and self.training: # shift
+            groupsz = int(q_len * getattr(self.config, "group_size_ratio"))
+            assert q_len % groupsz == 0, "q_len {} should be divisible by group size {}.".format(q_len, groupsz)
+            num_groups = q_len // groupsz
+            def shift(state: torch.Tensor) -> torch.Tensor:
+                state = state.transpose(1, 2) # output: (bsz, seq_len, n_heads, head_dim)
+                state = torch.cat((
+                    state[:, :, :self.num_heads//2], state[:, :, self.num_heads//2:].roll(-groupsz//2, dims=1)
+                ), dim=2)
+                return state.reshape(bsz * num_groups, groupsz, self.num_heads, self.head_dim).transpose(1, 2)
+
+            query_states, key_states, value_states = shift(query_states), shift(key_states), shift(value_states)
+            if attention_mask is not None:
+                attention_mask = attention_mask[:, :, :groupsz, :groupsz].repeat(num_groups, 1, 1, 1)
+
+        attn_weights = torch.matmul(query_states, key_states.transpose(2, 3)) / math.sqrt(self.head_dim)
+
+        if attention_mask is not None:
+            attn_weights = attn_weights + attention_mask
+
+        # upcast attention to fp32
+        attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype)
+        attn_output = torch.matmul(attn_weights, value_states) # (bsz, :, seq_len, :) or (bsz*n_group, :, groupsz, :)
+        attn_output = attn_output.transpose(1, 2).contiguous()
+
+        if getattr(self.config, "group_size_ratio", None) and self.training: # shift back
+            attn_output.reshape(bsz, q_len, self.num_heads, self.head_dim)
+            attn_output = torch.cat((
+                attn_output[:, :, :self.num_heads//2], attn_output[:, :, self.num_heads//2:].roll(groupsz//2, dims=1)
+            ))
+
+        attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
+        attn_output = self.o_proj(attn_output)
+
+        if not output_attentions:
+            attn_weights = None
+
+        return attn_output, attn_weights, past_key_value
+
+
+class LlamaFlashAttention2(LlamaAttention):
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_value: Optional[Tuple[torch.Tensor]] = None,
+        output_attentions: bool = False,
+        use_cache: bool = False,
+        **kwargs
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
+        # LlamaFlashAttention2 attention does not support output_attentions
+        output_attentions = False
+
+        bsz, q_len, _ = hidden_states.size()
+
+        query_states = self.q_proj(hidden_states)
+        key_states = self.k_proj(hidden_states)
+        value_states = self.v_proj(hidden_states)
+
+        # FlashAttention requires the input to have the shape (bsz, seq_len, n_heads, head_dim)
+        query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
+        key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+        value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+
+        kv_seq_len = key_states.shape[-2]
+        if past_key_value is not None:
+            kv_seq_len += past_key_value[0].shape[-2]
+
+        cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
+        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
+
+        if past_key_value is not None: # reuse k, v, self_attention
+            key_states = torch.cat([past_key_value[0], key_states], dim=2)
+            value_states = torch.cat([past_key_value[1], value_states], dim=2)
+
+        past_key_value = (key_states, value_states) if use_cache else None
+
+        # cast to half precision
+        input_dtype = query_states.dtype
+        if input_dtype == torch.float32:
+            logger.warning_once("The input hidden states seems to be silently casted in float32.")
+            query_states = query_states.to(self.config.torch_dtype)
+            key_states = key_states.to(self.config.torch_dtype)
+            value_states = value_states.to(self.config.torch_dtype)
+
+        if getattr(self, "num_key_value_groups", None):
+            key_states = repeat_kv(key_states, self.num_key_value_groups)
+            value_states = repeat_kv(value_states, self.num_key_value_groups)
+
+        query_states = query_states.transpose(1, 2) # (bsz, seq_len, n_heads, head_dim)
+        key_states = key_states.transpose(1, 2) # (bsz, seq_len, n_heads, head_dim)
+        value_states = value_states.transpose(1, 2) # (bsz, seq_len, n_heads, head_dim)
+
+        if getattr(self.config, "group_size_ratio", None) and self.training: # shift
+            groupsz = int(q_len * getattr(self.config, "group_size_ratio"))
+            assert q_len % groupsz == 0, "q_len {} should be divisible by group size {}.".format(q_len, groupsz)
+            num_groups = q_len // groupsz
+            def shift(state: torch.Tensor) -> torch.Tensor:
+                state = torch.cat((
+                    state[:, :, :self.num_heads//2], state[:, :, self.num_heads//2:].roll(-groupsz//2, dims=1)
+                ), dim=2)
+                return state.reshape(bsz * num_groups, groupsz, self.num_heads, self.head_dim)
+
+            query_states, key_states, value_states = shift(query_states), shift(key_states), shift(value_states)
+            if attention_mask is not None:
+                attention_mask = attention_mask.reshape(bsz * num_groups, groupsz)
+
+        if attention_mask is not None:
+            logger.warning_once("Padded sequences are less efficient in FlashAttention.")
+            # -q_len: assumes left padding when q_len != kv_len
+            unpadded_q, indices_q, cu_seqlens_q, max_seqlen_q = unpad_input(query_states, attention_mask[:, -q_len:])
+            unpadded_k, _, cu_seqlens_k, max_seqlen_k = unpad_input(key_states, attention_mask)
+            unpadded_v, _, _, _ = unpad_input(value_states, attention_mask)
+            attn_output_unpad = flash_attn_varlen_func(
+                unpadded_q,
+                unpadded_k,
+                unpadded_v,
+                cu_seqlens_q=cu_seqlens_q,
+                cu_seqlens_k=cu_seqlens_k,
+                max_seqlen_q=max_seqlen_q,
+                max_seqlen_k=max_seqlen_k,
+                dropout_p=0.0,
+                softmax_scale=None,
+                causal=True,
+            )
+            attn_output = pad_input(attn_output_unpad, indices_q, bsz, q_len)
+        else:
+            attn_output = flash_attn_func(
+                query_states, key_states, value_states, 0.0, softmax_scale=None, causal=True
+            )
+
+        if getattr(self.config, "group_size_ratio", None) and self.training: # shift back
+            attn_output.reshape(bsz, q_len, self.num_heads, self.head_dim)
+            attn_output = torch.cat((
+                attn_output[:, :, :self.num_heads//2], attn_output[:, :, self.num_heads//2:].roll(groupsz//2, dims=1)
+            ))
+
+        attn_output = attn_output.reshape(bsz, q_len, self.hidden_size).contiguous()
+        attn_output = self.o_proj(attn_output)
+
+        if not output_attentions:
+            attn_weights = None
+
+        return attn_output, attn_weights, past_key_value
+
+
+# Disable the transformation of the attention mask in LlamaModel as flash attention
+# takes a boolean padding_mask. Fills in the past kv length for use in forward.
+def _prepare_decoder_attention_mask(
+    self,
+    attention_mask: torch.Tensor,
+    input_shape: torch.Tensor,
+    inputs_embeds: torch.Tensor,
+    past_key_values_length: int
+) -> torch.Tensor:
+    if attention_mask is not None and torch.all(attention_mask):
+        return None  # This uses the faster call when training with full samples
+
+    return attention_mask

LLM-Detector-V7-11w/src/llmtuner/extras/ploting.py

@@ -0,0 +1,55 @@
+import os
+import math
+import json
+from typing import List, Optional
+from transformers.trainer import TRAINER_STATE_NAME
+
+from llmtuner.extras.logging import get_logger
+from llmtuner.extras.packages import is_matplotlib_available
+
+if is_matplotlib_available():
+    import matplotlib.pyplot as plt
+
+
+logger = get_logger(__name__)
+
+
+def smooth(scalars: List[float]) -> List[float]:
+    r"""
+    EMA implementation according to TensorBoard.
+    """
+    last = scalars[0]
+    smoothed = list()
+    weight = 1.8 * (1 / (1 + math.exp(-0.05 * len(scalars))) - 0.5) # a sigmoid function
+    for next_val in scalars:
+        smoothed_val = last * weight + (1 - weight) * next_val
+        smoothed.append(smoothed_val)
+        last = smoothed_val
+    return smoothed
+
+
+def plot_loss(save_dictionary: os.PathLike, keys: Optional[List[str]] = ["loss"]) -> None:
+
+    with open(os.path.join(save_dictionary, TRAINER_STATE_NAME), "r", encoding="utf-8") as f:
+        data = json.load(f)
+
+    for key in keys:
+        steps, metrics = [], []
+        for i in range(len(data["log_history"])):
+            if key in data["log_history"][i]:
+                steps.append(data["log_history"][i]["step"])
+                metrics.append(data["log_history"][i][key])
+
+        if len(metrics) == 0:
+            logger.warning(f"No metric {key} to plot.")
+            continue
+
+        plt.figure()
+        plt.plot(steps, metrics, alpha=0.4, label="original")
+        plt.plot(steps, smooth(metrics), label="smoothed")
+        plt.title("training {} of {}".format(key, save_dictionary))
+        plt.xlabel("step")
+        plt.ylabel(key)
+        plt.legend()
+        plt.savefig(os.path.join(save_dictionary, "training_{}.png".format(key)), format="png", dpi=100)
+        print("Figure saved:", os.path.join(save_dictionary, "training_{}.png".format(key)))

LLM-Detector-V7-11w/src/llmtuner/hparams/__init__.py

@@ -0,0 +1,5 @@
+from .data_args import DataArguments
+from .evaluation_args import EvaluationArguments
+from .finetuning_args import FinetuningArguments
+from .generating_args import GeneratingArguments
+from .model_args import ModelArguments

LLM-Detector-V7-11w/src/llmtuner/hparams/data_args.py

@@ -0,0 +1,189 @@
+import os
+import json
+from typing import List, Literal, Optional
+from dataclasses import dataclass, field
+
+
+DATA_CONFIG = "dataset_info.json"
+
+
+def use_modelscope() -> bool:
+    return bool(int(os.environ.get("USE_MODELSCOPE_HUB", "0")))
+
+
+@dataclass
+class DatasetAttr:
+
+    load_from: Literal["hf_hub", "ms_hub", "script", "file"]
+    dataset_name: Optional[str] = None
+    dataset_sha1: Optional[str] = None
+    subset: Optional[str] = None
+    folder: Optional[str] = None
+    ranking: Optional[bool] = False
+    formatting: Optional[Literal["alpaca", "sharegpt"]] = "alpaca"
+
+    prompt: Optional[str] = "instruction"
+    query: Optional[str] = "input"
+    response: Optional[str] = "output"
+    history: Optional[str] = None
+    messages: Optional[str] = "conversations"
+    role: Optional[str] = "from"
+    content: Optional[str] = "value"
+    system: Optional[str] = None
+
+    def __repr__(self) -> str:
+        return self.dataset_name
+
+
+@dataclass
+class DataArguments:
+    r"""
+    Arguments pertaining to what data we are going to input our model for training and evaluation.
+    """
+    template: Optional[str] = field(
+        default=None,
+        metadata={"help": "Which template to use for constructing prompts in training and inference."}
+    )
+    dataset: Optional[str] = field(
+        default=None,
+        metadata={"help": "The name of provided dataset(s) to use. Use commas to separate multiple datasets."}
+    )
+    dataset_dir: Optional[str] = field(
+        default="data",
+        metadata={"help": "Path to the folder containing the datasets."}
+    )
+    split: Optional[str] = field(
+        default="train",
+        metadata={"help": "Which dataset split to use for training and evaluation."}
+    )
+    cutoff_len: Optional[int] = field(
+        default=1024,
+        metadata={"help": "The maximum length of the model inputs after tokenization."}
+    )
+    reserved_label_len: Optional[int] = field(
+        default=1,
+        metadata={"help": "The maximum length reserved for label after tokenization."}
+    )
+    train_on_prompt: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether to disable the mask on the prompt or not."}
+    )
+    streaming: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Enable dataset streaming."}
+    )
+    buffer_size: Optional[int] = field(
+        default=16384,
+        metadata={"help": "Size of the buffer to randomly sample examples from in dataset streaming."}
+    )
+    mix_strategy: Optional[Literal["concat", "interleave_under", "interleave_over"]] = field(
+        default="concat",
+        metadata={"help": "Strategy to use in dataset mixing (concat/interleave) (undersampling/oversampling)."}
+    )
+    interleave_probs: Optional[str] = field(
+        default=None,
+        metadata={"help": "Probabilities to sample data from datasets. Use commas to separate multiple datasets."}
+    )
+    overwrite_cache: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Overwrite the cached training and evaluation sets."}
+    )
+    preprocessing_num_workers: Optional[int] = field(
+        default=None,
+        metadata={"help": "The number of processes to use for the preprocessing."}
+    )
+    max_samples: Optional[int] = field(
+        default=None,
+        metadata={"help": "For debugging purposes, truncate the number of examples for each dataset."}
+    )
+    eval_num_beams: Optional[int] = field(
+        default=None,
+        metadata={"help": "Number of beams to use for evaluation. This argument will be passed to `model.generate`"}
+    )
+    ignore_pad_token_for_loss: Optional[bool] = field(
+        default=True,
+        metadata={"help": "Whether to ignore the tokens corresponding to padded labels in the loss computation or not."}
+    )
+    val_size: Optional[float] = field(
+        default=0,
+        metadata={"help": "Size of the development set, should be an integer or a float in range `[0,1)`."}
+    )
+    sft_packing: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Packing the questions and answers in the supervised fine-tuning stage."}
+    )
+    cache_path: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to save or load the preprocessed datasets."}
+    )
+
+    def __post_init__(self):
+        if self.reserved_label_len >= self.cutoff_len:
+            raise ValueError("`reserved_label_len` must be smaller than `cutoff_len`.")
+
+        if self.streaming and self.val_size > 1e-6 and self.val_size < 1:
+            raise ValueError("Streaming mode should have an integer val size.")
+
+        if self.streaming and self.max_samples is not None:
+            raise ValueError("`max_samples` is incompatible with `streaming`.")
+
+    def init_for_training(self, seed: int): # support mixing multiple datasets
+        self.seed = seed
+        dataset_names = [ds.strip() for ds in self.dataset.split(",")] if self.dataset is not None else []
+        try:
+            with open(os.path.join(self.dataset_dir, DATA_CONFIG), "r") as f:
+                dataset_info = json.load(f)
+        except Exception as err:
+            if self.dataset is not None:
+                raise ValueError("Cannot open {} due to {}.".format(os.path.join(self.dataset_dir, DATA_CONFIG), str(err)))
+            dataset_info = None
+
+        if self.interleave_probs is not None:
+            self.interleave_probs = [float(prob.strip()) for prob in self.interleave_probs.split(",")]
+
+        self.dataset_list: List[DatasetAttr] = []
+        for name in dataset_names:
+            if name not in dataset_info:
+                raise ValueError("Undefined dataset {} in {}.".format(name, DATA_CONFIG))
+
+            has_hf_url = "hf_hub_url" in dataset_info[name]
+            has_ms_url = "ms_hub_url" in dataset_info[name]
+
+            if has_hf_url or has_ms_url:
+                if (use_modelscope() and has_ms_url) or (not has_hf_url):
+                    dataset_attr = DatasetAttr(
+                        "ms_hub",
+                        dataset_name=dataset_info[name]["ms_hub_url"]
+                    )
+                else:
+                    dataset_attr = DatasetAttr(
+                        "hf_hub",
+                        dataset_name=dataset_info[name]["hf_hub_url"]
+                    )
+            elif "script_url" in dataset_info[name]:
+                dataset_attr = DatasetAttr(
+                    "script",
+                    dataset_name=dataset_info[name]["script_url"]
+                )
+            else:
+                dataset_attr = DatasetAttr(
+                    "file",
+                    dataset_name=dataset_info[name]["file_name"],
+                    dataset_sha1=dataset_info[name].get("file_sha1", None)
+                )
+
+            if "columns" in dataset_info[name]:
+                dataset_attr.prompt = dataset_info[name]["columns"].get("prompt", None)
+                dataset_attr.query = dataset_info[name]["columns"].get("query", None)
+                dataset_attr.response = dataset_info[name]["columns"].get("response", None)
+                dataset_attr.history = dataset_info[name]["columns"].get("history", None)
+                dataset_attr.messages = dataset_info[name]["columns"].get("messages", None)
+                dataset_attr.role = dataset_info[name]["columns"].get("role", None)
+                dataset_attr.content = dataset_info[name]["columns"].get("content", None)
+                dataset_attr.system = dataset_info[name]["columns"].get("system", None)
+
+            dataset_attr.subset = dataset_info[name].get("subset", None)
+            dataset_attr.folder = dataset_info[name].get("folder", None)
+            dataset_attr.ranking = dataset_info[name].get("ranking", False)
+            dataset_attr.formatting = dataset_info[name].get("formatting", "alpaca")
+            self.dataset_list.append(dataset_attr)

LLM-Detector-V7-11w/src/llmtuner/hparams/evaluation_args.py

@@ -0,0 +1,55 @@
+import os
+from typing import Literal, Optional
+from dataclasses import dataclass, field
+
+from datasets import DownloadMode
+
+
+@dataclass
+class EvaluationArguments:
+    r"""
+    Arguments pertaining to specify the evaluation parameters.
+    """
+    task: str = field(
+        metadata={"help": "Name of the evaluation task."}
+    )
+    task_dir: Optional[str] = field(
+        default="evaluation",
+        metadata={"help": "Path to the folder containing the evaluation datasets."}
+    )
+    batch_size: Optional[int] = field(
+        default=4,
+        metadata={"help": "The batch size per GPU for evaluation."}
+    )
+    seed: Optional[int] = field(
+        default=42,
+        metadata={"help": "Random seed to be used with data loaders."}
+    )
+    lang: Optional[Literal["en", "zh"]] = field(
+        default="en",
+        metadata={"help": "Language used at evaluation."}
+    )
+    n_shot: Optional[int] = field(
+        default=5,
+        metadata={"help": "Number of examplars for few-shot learning."}
+    )
+    save_dir: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to save the evaluation results."}
+    )
+    download_mode: Optional[DownloadMode] = field(
+        default=DownloadMode.REUSE_DATASET_IF_EXISTS,
+        metadata={"help": "Download mode used for the evaluation datasets."}
+    )
+
+    def __post_init__(self):
+        task_available = []
+        for folder in os.listdir(self.task_dir):
+            if os.path.isdir(os.path.join(self.task_dir, folder)):
+                task_available.append(folder)
+
+        if self.task not in task_available:
+            raise ValueError("Task {} not found in {}.".format(self.task, self.task_dir))
+
+        if self.save_dir is not None and os.path.exists(self.save_dir):
+            raise ValueError("`save_dir` already exists, use another one.")

LLM-Detector-V7-11w/src/llmtuner/hparams/finetuning_args.py

@@ -0,0 +1,188 @@
+import json
+from typing import Literal, Optional
+from dataclasses import asdict, dataclass, field
+
+
+@dataclass
+class FreezeArguments:
+    r"""
+    Arguments pertaining to the freeze (partial-parameter) training.
+    """
+    name_module_trainable: Optional[str] = field(
+        default="mlp",
+        metadata={"help": "Name of trainable modules for partial-parameter (freeze) fine-tuning. \
+                  Use commas to separate multiple modules. \
+                  LLaMA choices: [\"mlp\", \"self_attn\"], \
+                  BLOOM & Falcon & ChatGLM choices: [\"mlp\", \"self_attention\"], \
+                  Qwen choices: [\"mlp\", \"attn\"], \
+                  Phi choices: [\"mlp\", \"mixer\"], \
+                  Others choices: the same as LLaMA."}
+    )
+    num_layer_trainable: Optional[int] = field(
+        default=3,
+        metadata={"help": "The number of trainable layers for partial-parameter (freeze) fine-tuning."}
+    )
+
+
+@dataclass
+class LoraArguments:
+    r"""
+    Arguments pertaining to the LoRA training.
+    """
+    additional_target: Optional[str] = field(
+        default=None,
+        metadata={"help": "Name(s) of modules apart from LoRA layers to be set as trainable and saved in the final checkpoint."}
+    )
+    lora_alpha: Optional[int] = field(
+        default=None,
+        metadata={"help": "The scale factor for LoRA fine-tuning (default: lora_rank * 2)."}
+    )
+    lora_dropout: Optional[float] = field(
+        default=0.0,
+        metadata={"help": "Dropout rate for the LoRA fine-tuning."}
+    )
+    lora_rank: Optional[int] = field(
+        default=8,
+        metadata={"help": "The intrinsic dimension for LoRA fine-tuning."}
+    )
+    lora_target: Optional[str] = field(
+        default=None,
+        metadata={"help": "Name(s) of target modules to apply LoRA. Use commas to separate multiple modules. \
+                  LLaMA choices: [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\"], \
+                  BLOOM & Falcon & ChatGLM choices: [\"query_key_value\", \"dense\", \"dense_h_to_4h\", \"dense_4h_to_h\"], \
+                  Baichuan choices: [\"W_pack\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\"], \
+                  Qwen choices: [\"c_attn\", \"attn.c_proj\", \"w1\", \"w2\", \"mlp.c_proj\"], \
+                  Phi choices: [\"Wqkv\", \"out_proj\", \"fc1\", \"fc2\"], \
+                  Others choices: the same as LLaMA."}
+    )
+    create_new_adapter: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether to create a new adapter with randomly initialized weight or not."}
+    )
+
+
+@dataclass
+class RLHFArguments:
+    r"""
+    Arguments pertaining to the PPO and DPO training.
+    """
+    dpo_beta: Optional[float] = field(
+        default=0.1,
+        metadata={"help": "The beta parameter for the DPO loss."}
+    )
+    dpo_loss: Optional[Literal["sigmoid", "hinge", "ipo", "kto"]] = field(
+        default="sigmoid",
+        metadata={"help": "The type of DPO loss to use."}
+    )
+    dpo_ftx: Optional[float] = field(
+        default=0,
+        metadata={"help": "The supervised fine-tuning loss coefficient in DPO training."}
+    )
+    ppo_buffer_size: Optional[int] = field(
+        default=1,
+        metadata={"help": "The number of mini-batches to make experience buffer in a PPO optimization step."}
+    )
+    ppo_epochs: Optional[int] = field(
+        default=4,
+        metadata={"help": "The number of epochs to perform in a PPO optimization step."}
+    )
+    ppo_logger: Optional[str] = field(
+        default=None,
+        metadata={"help": "Log with either \"wandb\" or \"tensorboard\" in PPO training."}
+    )
+    ppo_score_norm: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Use score normalization in PPO training."}
+    )
+    ppo_target: Optional[float] = field(
+        default=6.0,
+        metadata={"help": "Target KL value for adaptive KL control in PPO training."}
+    )
+    ppo_whiten_rewards: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whiten the rewards before compute advantages in PPO training."}
+    )
+    ref_model: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to the reference model used for the PPO or DPO training."}
+    )
+    ref_model_adapters: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to the adapters of the reference model."}
+    )
+    ref_model_quantization_bit: Optional[int] = field(
+        default=None,
+        metadata={"help": "The number of bits to quantize the reference model."}
+    )
+    reward_model: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to the reward model used for the PPO training."}
+    )
+    reward_model_adapters: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to the adapters of the reward model."}
+    )
+    reward_model_quantization_bit: Optional[int] = field(
+        default=None,
+        metadata={"help": "The number of bits to quantize the reward model."}
+    )
+    reward_model_type: Optional[Literal["lora", "full", "api"]] = field(
+        default="lora",
+        metadata={"help": "The type of the reward model in PPO training. Lora model only supports lora training."}
+    )
+
+
+@dataclass
+class FinetuningArguments(FreezeArguments, LoraArguments, RLHFArguments):
+    r"""
+    Arguments pertaining to which techniques we are going to fine-tuning with.
+    """
+    stage: Optional[Literal["pt", "sft", "rm", "ppo", "dpo"]] = field(
+        default="sft",
+        metadata={"help": "Which stage will be performed in training."}
+    )
+    finetuning_type: Optional[Literal["lora", "freeze", "full"]] = field(
+        default="lora",
+        metadata={"help": "Which fine-tuning method to use."}
+    )
+    plot_loss: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not to save the training loss curves."}
+    )
+
+    def __post_init__(self):
+        def split_arg(arg):
+            if isinstance(arg, str):
+                return [item.strip() for item in arg.split(",")]
+            return arg
+
+        self.name_module_trainable = split_arg(self.name_module_trainable)
+        self.lora_alpha = self.lora_alpha or self.lora_rank * 2
+        self.lora_target = split_arg(self.lora_target)
+        self.additional_target = split_arg(self.additional_target)
+        self.ref_model_adapters = split_arg(self.ref_model_adapters)
+        self.reward_model_adapters = split_arg(self.reward_model_adapters)
+
+        assert self.finetuning_type in ["lora", "freeze", "full"], "Invalid fine-tuning method."
+        assert self.ref_model_quantization_bit in [None, 8, 4], "We only accept 4-bit or 8-bit quantization."
+        assert self.reward_model_quantization_bit in [None, 8, 4], "We only accept 4-bit or 8-bit quantization."
+
+        if self.stage == "ppo" and self.reward_model is None:
+            raise ValueError("Reward model is necessary for PPO training.")
+
+        if self.stage == "ppo" and self.reward_model_type == "lora" and self.finetuning_type != "lora":
+            raise ValueError("Freeze/Full PPO training needs `reward_model_type=full`.")
+
+    def save_to_json(self, json_path: str):
+        r"""Saves the content of this instance in JSON format inside `json_path`."""
+        json_string = json.dumps(asdict(self), indent=2, sort_keys=True) + "\n"
+        with open(json_path, "w", encoding="utf-8") as f:
+            f.write(json_string)
+
+    @classmethod
+    def load_from_json(cls, json_path: str):
+        r"""Creates an instance from the content of `json_path`."""
+        with open(json_path, "r", encoding="utf-8") as f:
+            text = f.read()
+
+        return cls(**json.loads(text))

LLM-Detector-V7-11w/src/llmtuner/hparams/generating_args.py

@@ -0,0 +1,53 @@
+from typing import Any, Dict, Optional
+from dataclasses import asdict, dataclass, field
+
+
+@dataclass
+class GeneratingArguments:
+    r"""
+    Arguments pertaining to specify the decoding parameters.
+    """
+    do_sample: Optional[bool] = field(
+        default=True,
+        metadata={"help": "Whether or not to use sampling, use greedy decoding otherwise."}
+    )
+    temperature: Optional[float] = field(
+        default=0.95,
+        metadata={"help": "The value used to modulate the next token probabilities."}
+    )
+    top_p: Optional[float] = field(
+        default=0.7,
+        metadata={"help": "The smallest set of most probable tokens with probabilities that add up to top_p or higher are kept."}
+    )
+    top_k: Optional[int] = field(
+        default=50,
+        metadata={"help": "The number of highest probability vocabulary tokens to keep for top-k filtering."}
+    )
+    num_beams: Optional[int] = field(
+        default=1,
+        metadata={"help": "Number of beams for beam search. 1 means no beam search."}
+    )
+    max_length: Optional[int] = field(
+        default=512,
+        metadata={"help": "The maximum length the generated tokens can have. It can be overridden by max_new_tokens."}
+    )
+    max_new_tokens: Optional[int] = field(
+        default=512,
+        metadata={"help": "The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt."}
+    )
+    repetition_penalty: Optional[float] = field(
+        default=1.0,
+        metadata={"help": "The parameter for repetition penalty. 1.0 means no penalty."}
+    )
+    length_penalty: Optional[float] = field(
+        default=1.0,
+        metadata={"help": "Exponential penalty to the length that is used with beam-based generation."}
+    )
+
+    def to_dict(self) -> Dict[str, Any]:
+        args = asdict(self)
+        if args.get("max_new_tokens", -1) > 0:
+            args.pop("max_length", None)
+        else:
+            args.pop("max_new_tokens", None)
+        return args

LLM-Detector-V7-11w/src/llmtuner/hparams/model_args.py

@@ -0,0 +1,127 @@
+from typing import Any, Dict, Literal, Optional
+from dataclasses import asdict, dataclass, field
+
+
+@dataclass
+class ModelArguments:
+    r"""
+    Arguments pertaining to which model/config/tokenizer we are going to fine-tune.
+    """
+    model_name_or_path: str = field(
+        metadata={"help": "Path to the model weight or identifier from huggingface.co/models or modelscope.cn/models."}
+    )
+    adapter_name_or_path: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to the adapter weight or identifier from huggingface.co/models."}
+    )
+    cache_dir: Optional[str] = field(
+        default=None,
+        metadata={"help": "Where to store the pre-trained models downloaded from huggingface.co or modelscope.cn."}
+    )
+    use_fast_tokenizer: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not to use one of the fast tokenizer (backed by the tokenizers library)."}
+    )
+    resize_vocab: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not to resize the tokenizer vocab and the embedding layers."}
+    )
+    split_special_tokens: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not the special tokens should be split during the tokenization process."}
+    )
+    model_revision: Optional[str] = field(
+        default="main",
+        metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."}
+    )
+    quantization_bit: Optional[int] = field(
+        default=None,
+        metadata={"help": "The number of bits to quantize the model."}
+    )
+    quantization_type: Optional[Literal["fp4", "nf4"]] = field(
+        default="nf4",
+        metadata={"help": "Quantization data type to use in int4 training."}
+    )
+    double_quantization: Optional[bool] = field(
+        default=True,
+        metadata={"help": "Whether or not to use double quantization in int4 training."}
+    )
+    rope_scaling: Optional[Literal["linear", "dynamic"]] = field(
+        default=None,
+        metadata={"help": "Which scaling strategy should be adopted for the RoPE embeddings."}
+    )
+    flash_attn: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Enable FlashAttention-2 for faster training."}
+    )
+    shift_attn: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Enable shift short attention (S^2-Attn) proposed by LongLoRA."}
+    )
+    use_unsloth: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not to use unsloth's optimization for the LoRA training."}
+    )
+    disable_gradient_checkpointing: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not to disable gradient checkpointing."}
+    )
+    upcast_layernorm: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not to upcast the layernorm weights in fp32."}
+    )
+    hf_hub_token: Optional[str] = field(
+        default=None,
+        metadata={"help": "Auth token to log in with Hugging Face Hub."}
+    )
+    ms_hub_token: Optional[str] = field(
+        default=None,
+        metadata={"help": "Auth token to log in with ModelScope Hub."}
+    )
+    export_dir: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to the directory to save the exported model."}
+    )
+    export_size: Optional[int] = field(
+        default=1,
+        metadata={"help": "The file shard size (in GB) of the exported model."}
+    )
+    export_quantization_bit: Optional[int] = field(
+        default=None,
+        metadata={"help": "The number of bits to quantize the exported model."}
+    )
+    export_quantization_dataset: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to the dataset or dataset name to use in quantizing the exported model."}
+    )
+    export_quantization_nsamples: Optional[int] = field(
+        default=128,
+        metadata={"help": "The number of samples used for quantization."}
+    )
+    export_quantization_maxlen: Optional[int] = field(
+        default=1024,
+        metadata={"help": "The maximum length of the model inputs used for quantization."}
+    )
+    export_legacy_format: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Whether or not to save the `.bin` files instead of `.safetensors`."}
+    )
+
+    def __post_init__(self):
+        self.compute_dtype = None
+        self.model_max_length = None
+
+        if self.split_special_tokens and self.use_fast_tokenizer:
+            raise ValueError("`split_special_tokens` is only supported for slow tokenizers.")
+
+        if self.adapter_name_or_path is not None: # support merging multiple lora weights
+            self.adapter_name_or_path = [path.strip() for path in self.adapter_name_or_path.split(",")]
+
+        assert self.quantization_bit in [None, 8, 4], "We only accept 4-bit or 8-bit quantization."
+        assert self.export_quantization_bit in [None, 8, 4, 3, 2], "We only accept 2/3/4/8-bit quantization."
+
+        if self.export_quantization_bit is not None and self.export_quantization_dataset is None:
+            raise ValueError("Quantization dataset is necessary for exporting.")
+
+    def to_dict(self) -> Dict[str, Any]:
+        return asdict(self)

LLM-Detector-V7-11w/src/llmtuner/model/__init__.py

@@ -0,0 +1,5 @@
+# Level: loader > adapter > parser, utils
+
+from llmtuner.model.loader import load_model_and_tokenizer
+from llmtuner.model.parser import get_train_args, get_infer_args, get_eval_args
+from llmtuner.model.utils import dispatch_model, get_modelcard_args, load_valuehead_params

LLM-Detector-V7-11w/src/llmtuner/model/adapter.py

@@ -0,0 +1,133 @@
+import torch
+from typing import TYPE_CHECKING
+from transformers.integrations import is_deepspeed_zero3_enabled
+from peft import PeftModel, TaskType, LoraConfig, get_peft_model
+
+from llmtuner.extras.logging import get_logger
+from llmtuner.model.utils import find_all_linear_modules
+
+if TYPE_CHECKING:
+    from transformers.modeling_utils import PreTrainedModel
+    from llmtuner.hparams import ModelArguments, FinetuningArguments
+
+
+logger = get_logger(__name__)
+
+
+def init_adapter(
+    model: "PreTrainedModel",
+    model_args: "ModelArguments",
+    finetuning_args: "FinetuningArguments",
+    is_trainable: bool
+) -> "PreTrainedModel":
+    r"""
+    Initializes the adapters.
+
+    Support full-parameter, freeze and LoRA training.
+
+    Note that the trainable parameters must be cast to float32.
+    """
+
+    if (not is_trainable) and model_args.adapter_name_or_path is None:
+        logger.info("Adapter is not found at evaluation, load the base model.")
+        return model
+
+    if finetuning_args.finetuning_type == "full" and is_trainable:
+        logger.info("Fine-tuning method: Full")
+        model = model.float()
+
+    if finetuning_args.finetuning_type == "freeze" and is_trainable:
+        logger.info("Fine-tuning method: Freeze")
+        num_layers = (
+            getattr(model.config, "num_hidden_layers", None)
+            or getattr(model.config, "num_layers", None)
+            or getattr(model.config, "n_layer", None)
+        )
+        if not num_layers:
+            raise ValueError("Current model does not support freeze tuning.")
+
+        if finetuning_args.num_layer_trainable > 0: # fine-tuning the last n layers if num_layer_trainable > 0
+            trainable_layer_ids = [num_layers - k - 1 for k in range(finetuning_args.num_layer_trainable)]
+        else: # fine-tuning the first n layers if num_layer_trainable < 0
+            trainable_layer_ids = [k for k in range(-finetuning_args.num_layer_trainable)]
+
+        trainable_layers = []
+        for module_name in finetuning_args.name_module_trainable:
+            for idx in trainable_layer_ids:
+                trainable_layers.append("{:d}.{}".format(idx, module_name))
+
+        for name, param in model.named_parameters():
+            if not any(trainable_layer in name for trainable_layer in trainable_layers):
+                param.requires_grad_(False)
+            else:
+                param.data = param.data.to(torch.float32)
+
+    if finetuning_args.finetuning_type == "lora":
+        logger.info("Fine-tuning method: LoRA")
+        adapter_to_resume = None
+
+        if model_args.adapter_name_or_path is not None:
+            is_mergeable = True
+            if getattr(model, "quantization_method", None): # merge lora in quantized model is unstable
+                assert len(model_args.adapter_name_or_path) == 1, "Quantized model only accepts a single adapter."
+                is_mergeable = False
+
+            if is_deepspeed_zero3_enabled():
+                assert len(model_args.adapter_name_or_path) == 1, "Cannot use multiple adapters in DeepSpeed ZeRO-3."
+                is_mergeable = False
+
+            if (is_trainable and not finetuning_args.create_new_adapter) or (not is_mergeable):
+                adapter_to_merge = model_args.adapter_name_or_path[:-1]
+                adapter_to_resume = model_args.adapter_name_or_path[-1]
+            else:
+                adapter_to_merge = model_args.adapter_name_or_path
+
+            for adapter in adapter_to_merge:
+                model = PeftModel.from_pretrained(model, adapter)
+                model = model.merge_and_unload()
+
+            if len(adapter_to_merge) > 0:
+                logger.info("Merged {} adapter(s).".format(len(adapter_to_merge)))
+
+            if adapter_to_resume is not None: # resume lora training
+                model = PeftModel.from_pretrained(model, adapter_to_resume, is_trainable=is_trainable)
+
+        if is_trainable and adapter_to_resume is None: # create new lora weights while training
+            if len(finetuning_args.lora_target) == 1 and finetuning_args.lora_target[0] == "all":
+                target_modules = find_all_linear_modules(model)
+            else:
+                target_modules = finetuning_args.lora_target
+
+            peft_kwargs = {
+                "r": finetuning_args.lora_rank,
+                "target_modules": target_modules,
+                "lora_alpha": finetuning_args.lora_alpha,
+                "lora_dropout": finetuning_args.lora_dropout
+            }
+
+            if model_args.use_unsloth:
+                from unsloth import FastLlamaModel, FastMistralModel # type: ignore
+                unsloth_peft_kwargs = {"model": model, "max_seq_length": model_args.model_max_length}
+                if getattr(model.config, "model_type", None) == "llama":
+                    model = FastLlamaModel.get_peft_model(**peft_kwargs, **unsloth_peft_kwargs)
+                elif getattr(model.config, "model_type", None) == "mistral":
+                    model = FastMistralModel.get_peft_model(**peft_kwargs, **unsloth_peft_kwargs)
+                else:
+                    raise NotImplementedError
+
+            else:
+                lora_config = LoraConfig(
+                    task_type=TaskType.CAUSAL_LM,
+                    inference_mode=False,
+                    modules_to_save=finetuning_args.additional_target,
+                    **peft_kwargs
+                )
+                model = get_peft_model(model, lora_config)
+
+        for param in filter(lambda p: p.requires_grad, model.parameters()):
+            param.data = param.data.to(torch.float32)
+
+    if model_args.adapter_name_or_path is not None:
+        logger.info("Loaded adapter(s): {}".format(",".join(model_args.adapter_name_or_path)))
+
+    return model

LLM-Detector-V7-11w/src/llmtuner/model/loader.py

@@ -0,0 +1,129 @@
+from typing import TYPE_CHECKING, Optional, Tuple
+from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
+from transformers.integrations import is_deepspeed_zero3_enabled
+from transformers.utils.versions import require_version
+from trl import AutoModelForCausalLMWithValueHead
+
+from llmtuner.extras.logging import get_logger
+from llmtuner.extras.misc import count_parameters, get_current_device, try_download_model_from_ms
+from llmtuner.model.adapter import init_adapter
+from llmtuner.model.patcher import patch_config, patch_tokenizer, patch_model, patch_valuehead_model
+from llmtuner.model.utils import load_valuehead_params, register_autoclass
+
+if TYPE_CHECKING:
+    from transformers import PreTrainedModel, PreTrainedTokenizer
+    from llmtuner.hparams import ModelArguments, FinetuningArguments
+
+
+logger = get_logger(__name__)
+
+
+require_version("transformers>=4.36.2", "To fix: pip install transformers>=4.36.2")
+require_version("datasets>=2.14.3", "To fix: pip install datasets>=2.14.3")
+require_version("accelerate>=0.21.0", "To fix: pip install accelerate>=0.21.0")
+require_version("peft>=0.7.0", "To fix: pip install peft>=0.7.0")
+require_version("trl>=0.7.6", "To fix: pip install trl>=0.7.6")
+
+
+def load_model_and_tokenizer(
+    model_args: "ModelArguments",
+    finetuning_args: "FinetuningArguments",
+    is_trainable: Optional[bool] = False,
+    add_valuehead: Optional[bool] = False
+) -> Tuple["PreTrainedModel", "PreTrainedTokenizer"]:
+    r"""
+    Loads pretrained model and tokenizer.
+
+    Support both training and inference.
+    """
+
+    try_download_model_from_ms(model_args)
+
+    config_kwargs = {
+        "trust_remote_code": True,
+        "cache_dir": model_args.cache_dir,
+        "revision": model_args.model_revision,
+        "token": model_args.hf_hub_token
+    }
+
+    tokenizer = AutoTokenizer.from_pretrained(
+        model_args.model_name_or_path,
+        use_fast=model_args.use_fast_tokenizer,
+        split_special_tokens=model_args.split_special_tokens,
+        padding_side="right",
+        **config_kwargs
+    )
+    patch_tokenizer(tokenizer)
+
+    config = AutoConfig.from_pretrained(model_args.model_name_or_path, **config_kwargs)
+    patch_config(config, tokenizer, model_args, config_kwargs, is_trainable)
+
+    model = None
+    if is_trainable and model_args.use_unsloth:
+        require_version("unsloth", "Follow the instructions at: https://github.com/unslothai/unsloth")
+        from unsloth import FastLlamaModel, FastMistralModel # type: ignore
+        unsloth_kwargs = {
+            "model_name": model_args.model_name_or_path,
+            "max_seq_length": model_args.model_max_length,
+            "dtype": model_args.compute_dtype,
+            "load_in_4bit": model_args.quantization_bit == 4,
+            "token": model_args.hf_hub_token,
+            "device_map": get_current_device(),
+            "rope_scaling": getattr(config, "rope_scaling", None)
+        }
+        if getattr(config, "model_type", None) == "llama":
+            model, _ = FastLlamaModel.from_pretrained(**unsloth_kwargs)
+        elif getattr(config, "model_type", None) == "mistral":
+            model, _ = FastMistralModel.from_pretrained(**unsloth_kwargs)
+        else:
+            logger.warning("Unsloth does not support model type {}.".format(getattr(config, "model_type", None)))
+            model_args.use_unsloth = False
+
+        if model_args.adapter_name_or_path:
+            model_args.adapter_name_or_path = None
+            logger.warning("Unsloth does not support loading adapters.")
+
+    if model is None:
+        model = AutoModelForCausalLM.from_pretrained(
+            model_args.model_name_or_path,
+            config=config,
+            torch_dtype=model_args.compute_dtype,
+            low_cpu_mem_usage=(not is_deepspeed_zero3_enabled()),
+            **config_kwargs
+        )
+
+    patch_model(model, tokenizer, model_args, is_trainable)
+    register_autoclass(config, model, tokenizer)
+
+    model = init_adapter(model, model_args, finetuning_args, is_trainable)
+
+    if add_valuehead:
+        model: "AutoModelForCausalLMWithValueHead" = AutoModelForCausalLMWithValueHead.from_pretrained(model)
+        patch_valuehead_model(model)
+
+        if model_args.adapter_name_or_path is not None:
+            vhead_path = model_args.adapter_name_or_path[-1]
+        else:
+            vhead_path = model_args.model_name_or_path
+
+        vhead_params = load_valuehead_params(vhead_path, model_args)
+        if vhead_params is not None:
+            model.load_state_dict(vhead_params, strict=False)
+            logger.info("Loaded valuehead from checkpoint: {}".format(vhead_path))
+
+    if not is_trainable:
+        model.requires_grad_(False)
+        model = model.to(model_args.compute_dtype) if not getattr(model, "quantization_method", None) else model
+        model.eval()
+    else:
+        model.train()
+
+    trainable_params, all_param = count_parameters(model)
+    logger.info("trainable params: {:d} || all params: {:d} || trainable%: {:.4f}".format(
+        trainable_params, all_param, 100 * trainable_params / all_param
+    ))
+
+    if not is_trainable:
+        logger.info("This IS expected that the trainable params is 0 if you are using model for inference only.")
+
+    return model, tokenizer

LLM-Detector-V7-11w/src/llmtuner/model/parser.py

@@ -0,0 +1,246 @@
+import os
+import sys
+import torch
+import logging
+import datasets
+import transformers
+from typing import Any, Dict, Optional, Tuple
+from transformers import HfArgumentParser, Seq2SeqTrainingArguments
+from transformers.trainer_utils import get_last_checkpoint
+
+from llmtuner.extras.logging import get_logger
+from llmtuner.hparams import (
+    ModelArguments,
+    DataArguments,
+    EvaluationArguments,
+    FinetuningArguments,
+    GeneratingArguments
+)
+
+
+logger = get_logger(__name__)
+
+
+_TRAIN_ARGS = [
+    ModelArguments, DataArguments, Seq2SeqTrainingArguments, FinetuningArguments, GeneratingArguments
+]
+_TRAIN_CLS = Tuple[
+    ModelArguments, DataArguments, Seq2SeqTrainingArguments, FinetuningArguments, GeneratingArguments
+]
+_INFER_ARGS = [
+    ModelArguments, DataArguments, FinetuningArguments, GeneratingArguments
+]
+_INFER_CLS = Tuple[
+    ModelArguments, DataArguments, FinetuningArguments, GeneratingArguments
+]
+_EVAL_ARGS = [
+    ModelArguments, DataArguments, EvaluationArguments, FinetuningArguments
+]
+_EVAL_CLS = Tuple[
+    ModelArguments, DataArguments, EvaluationArguments, FinetuningArguments
+]
+
+
+def _parse_args(parser: "HfArgumentParser", args: Optional[Dict[str, Any]] = None) -> Tuple[Any]:
+    if args is not None:
+        return parser.parse_dict(args)
+
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".yaml"):
+        return parser.parse_yaml_file(os.path.abspath(sys.argv[1]))
+
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
+        return parser.parse_json_file(os.path.abspath(sys.argv[1]))
+
+    (*parsed_args, unknown_args) = parser.parse_args_into_dataclasses(return_remaining_strings=True)
+
+    if unknown_args:
+        print(parser.format_help())
+        print("Got unknown args, potentially deprecated arguments: {}".format(unknown_args))
+        raise ValueError("Some specified arguments are not used by the HfArgumentParser: {}".format(unknown_args))
+
+    return (*parsed_args,)
+
+
+def _set_transformers_logging(log_level: Optional[int] = logging.INFO) -> None:
+    datasets.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.enable_default_handler()
+    transformers.utils.logging.enable_explicit_format()
+
+
+def _verify_model_args(model_args: "ModelArguments", finetuning_args: "FinetuningArguments") -> None:
+    if model_args.quantization_bit is not None:
+        if finetuning_args.finetuning_type != "lora":
+            raise ValueError("Quantization is only compatible with the LoRA method.")
+
+        if finetuning_args.create_new_adapter:
+            raise ValueError("Cannot create new adapter upon a quantized model.")
+
+    if model_args.adapter_name_or_path is not None and len(model_args.adapter_name_or_path) != 1:
+        if finetuning_args.finetuning_type != "lora":
+            raise ValueError("Multiple adapters are only available for LoRA tuning.")
+        
+        if model_args.quantization_bit is not None:
+            raise ValueError("Quantized model only accepts a single adapter. Merge them first.")
+
+
+def _parse_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
+    parser = HfArgumentParser(_TRAIN_ARGS)
+    return _parse_args(parser, args)
+
+
+def _parse_infer_args(args: Optional[Dict[str, Any]] = None) -> _INFER_CLS:
+    parser = HfArgumentParser(_INFER_ARGS)
+    return _parse_args(parser, args)
+
+
+def _parse_eval_args(args: Optional[Dict[str, Any]] = None) -> _EVAL_CLS:
+    parser = HfArgumentParser(_EVAL_ARGS)
+    return _parse_args(parser, args)
+
+
+def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
+    model_args, data_args, training_args, finetuning_args, generating_args = _parse_train_args(args)
+
+    # Setup logging
+    if training_args.should_log:
+        _set_transformers_logging()
+
+    # Check arguments
+    data_args.init_for_training(training_args.seed)
+
+    if finetuning_args.stage != "pt" and data_args.template is None:
+        raise ValueError("Please specify which `template` to use.")
+
+    if finetuning_args.stage != "sft" and training_args.predict_with_generate:
+        raise ValueError("`predict_with_generate` cannot be set as True except SFT.")
+
+    if finetuning_args.stage == "sft" and training_args.do_predict and not training_args.predict_with_generate:
+        raise ValueError("Please enable `predict_with_generate` to save model predictions.")
+
+    if finetuning_args.stage in ["rm", "ppo"] and training_args.load_best_model_at_end:
+        raise ValueError("RM and PPO stages do not support `load_best_model_at_end`.")
+
+    if finetuning_args.stage == "ppo" and not training_args.do_train:
+        raise ValueError("PPO training does not support evaluation, use the SFT stage to evaluate models.")
+
+    if finetuning_args.stage in ["rm", "dpo"] and (not all([data_attr.ranking for data_attr in data_args.dataset_list])):
+        raise ValueError("Please use ranked datasets for reward modeling or DPO training.")
+
+    if finetuning_args.stage == "ppo" and model_args.shift_attn:
+        raise ValueError("PPO training is incompatible with S^2-Attn.")
+
+    if finetuning_args.stage == "ppo" and finetuning_args.reward_model_type == "lora" and model_args.use_unsloth:
+        raise ValueError("Unsloth does not support lora reward model.")
+
+    if training_args.max_steps == -1 and data_args.streaming:
+        raise ValueError("Please specify `max_steps` in streaming mode.")
+
+    if training_args.do_train and training_args.predict_with_generate:
+        raise ValueError("`predict_with_generate` cannot be set as True while training.")
+
+    if training_args.do_train and finetuning_args.finetuning_type == "lora" and finetuning_args.lora_target is None:
+        raise ValueError("Please specify `lora_target` in LoRA training.")
+
+    _verify_model_args(model_args, finetuning_args)
+
+    if training_args.do_train and model_args.quantization_bit is not None and (not model_args.upcast_layernorm):
+        logger.warning("We recommend enable `upcast_layernorm` in quantized training.")
+
+    if training_args.do_train and (not training_args.fp16) and (not training_args.bf16):
+        logger.warning("We recommend enable mixed precision training.")
+
+    if (not training_args.do_train) and model_args.quantization_bit is not None:
+        logger.warning("Evaluating model in 4/8-bit mode may cause lower scores.")
+
+    if (not training_args.do_train) and finetuning_args.stage == "dpo" and finetuning_args.ref_model is None:
+        logger.warning("Specify `ref_model` for computing rewards at evaluation.")
+
+    # postprocess training_args
+    if (
+        training_args.local_rank != -1
+        and training_args.ddp_find_unused_parameters is None
+        and finetuning_args.finetuning_type == "lora"
+    ):
+        logger.warning("`ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.")
+        training_args_dict = training_args.to_dict()
+        training_args_dict.update(dict(ddp_find_unused_parameters=False))
+        training_args = Seq2SeqTrainingArguments(**training_args_dict)
+
+    if finetuning_args.stage in ["rm", "ppo"] and finetuning_args.finetuning_type in ["full", "freeze"]:
+        can_resume_from_checkpoint = False
+        training_args.resume_from_checkpoint = None
+    else:
+        can_resume_from_checkpoint = True
+
+    if (
+        training_args.resume_from_checkpoint is None
+        and training_args.do_train
+        and os.path.isdir(training_args.output_dir)
+        and not training_args.overwrite_output_dir
+        and can_resume_from_checkpoint
+    ):
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError("Output directory already exists and is not empty. Please set `overwrite_output_dir`.")
+
+        if last_checkpoint is not None:
+            training_args_dict = training_args.to_dict()
+            training_args_dict.update(dict(resume_from_checkpoint=last_checkpoint))
+            training_args = Seq2SeqTrainingArguments(**training_args_dict)
+            logger.info("Resuming training from {}. Change `output_dir` or use `overwrite_output_dir` to avoid.".format(
+                training_args.resume_from_checkpoint
+            ))
+
+    if (
+        finetuning_args.stage in ["rm", "ppo"]
+        and finetuning_args.finetuning_type == "lora"
+        and training_args.resume_from_checkpoint is not None
+    ):
+        logger.warning("Add {} to `adapter_name_or_path` to resume training from checkpoint.".format(
+            training_args.resume_from_checkpoint
+        ))
+
+    # postprocess model_args
+    model_args.compute_dtype = (
+        torch.bfloat16 if training_args.bf16 else (torch.float16 if training_args.fp16 else None)
+    )
+    model_args.model_max_length = data_args.cutoff_len
+
+    # Log on each process the small summary:
+    logger.info("Process rank: {}, device: {}, n_gpu: {}\n  distributed training: {}, compute dtype: {}".format(
+        training_args.local_rank, training_args.device, training_args.n_gpu,
+        bool(training_args.local_rank != -1), str(model_args.compute_dtype)
+    ))
+    logger.info(f"Training/evaluation parameters {training_args}")
+
+    # Set seed before initializing model.
+    transformers.set_seed(training_args.seed)
+
+    return model_args, data_args, training_args, finetuning_args, generating_args
+
+
+def get_infer_args(args: Optional[Dict[str, Any]] = None) -> _INFER_CLS:
+    model_args, data_args, finetuning_args, generating_args = _parse_infer_args(args)
+    _set_transformers_logging()
+
+    if data_args.template is None:
+        raise ValueError("Please specify which `template` to use.")
+
+    _verify_model_args(model_args, finetuning_args)
+
+    return model_args, data_args, finetuning_args, generating_args
+
+
+def get_eval_args(args: Optional[Dict[str, Any]] = None) -> _EVAL_CLS:
+    model_args, data_args, eval_args, finetuning_args = _parse_eval_args(args)
+    _set_transformers_logging()
+
+    if data_args.template is None:
+        raise ValueError("Please specify which `template` to use.")
+
+    _verify_model_args(model_args, finetuning_args)
+
+    transformers.set_seed(eval_args.seed)
+
+    return model_args, data_args, eval_args, finetuning_args

LLM-Detector-V7-11w/src/llmtuner/model/patcher.py

@@ -0,0 +1,288 @@
+import os
+import math
+import torch
+import random
+from types import MethodType
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
+from datasets import load_dataset
+
+from transformers import BitsAndBytesConfig, GPTQConfig, PreTrainedModel, PreTrainedTokenizerBase
+from transformers.integrations import is_deepspeed_zero3_enabled
+from transformers.utils.versions import require_version
+
+from llmtuner.extras.constants import FILEEXT2TYPE, LAYERNORM_NAMES
+from llmtuner.extras.logging import get_logger
+from llmtuner.extras.misc import get_current_device, infer_optim_dtype
+from llmtuner.extras.packages import is_flash_attn2_available
+
+if TYPE_CHECKING:
+    from transformers import PretrainedConfig, PreTrainedTokenizer
+    from trl import AutoModelForCausalLMWithValueHead
+    from llmtuner.hparams import ModelArguments
+
+
+logger = get_logger(__name__)
+SUPPORTED_CLASS_FOR_S2ATTN = [] # TODO: add llama
+
+
+def _noisy_mean_initialization(embed_weight: torch.Tensor, num_new_tokens: int):
+    embedding_dim = embed_weight.size(1)
+    avg_weight = embed_weight[:-num_new_tokens].mean(dim=0, keepdim=True)
+    noise_weight = torch.empty_like(avg_weight[-num_new_tokens:])
+    noise_weight.normal_(mean=0, std=(1.0 / math.sqrt(embedding_dim)))
+    embed_weight[-num_new_tokens:] = avg_weight + noise_weight
+
+
+def _resize_embedding_layer(model: "PreTrainedModel", tokenizer: "PreTrainedTokenizer") -> None:
+    r"""
+    Resize token embeddings.
+    """
+    current_embedding_size = model.get_input_embeddings().weight.size(0)
+    if len(tokenizer) > current_embedding_size:
+        if not isinstance(model.get_output_embeddings(), torch.nn.Linear):
+            logger.warning("Current model does not support resizing token embeddings.")
+            return
+
+        model.resize_token_embeddings(len(tokenizer), pad_to_multiple_of=64)
+        new_embedding_size = model.get_input_embeddings().weight.size(0)
+        num_new_tokens = new_embedding_size - current_embedding_size
+        _noisy_mean_initialization(model.get_input_embeddings().weight.data, num_new_tokens)
+        _noisy_mean_initialization(model.get_output_embeddings().weight.data, num_new_tokens)
+
+        logger.info("Resized token embeddings from {} to {}.".format(current_embedding_size, new_embedding_size))
+
+
+def _get_quantization_dataset(tokenizer: "PreTrainedTokenizer", model_args: "ModelArguments") -> List[str]:
+    r"""
+    Inspired by: https://github.com/huggingface/optimum/blob/v1.16.0/optimum/gptq/data.py#L133
+    TODO: remove tokenizer.decode() https://github.com/huggingface/optimum/pull/1600
+    """
+    if os.path.isfile(model_args.export_quantization_dataset):
+        data_path = FILEEXT2TYPE.get(model_args.export_quantization_dataset.split(".")[-1], None)
+        data_files = model_args.export_quantization_dataset
+    else:
+        data_path = model_args.export_quantization_dataset
+        data_files = None
+
+    dataset = load_dataset(path=data_path, data_files=data_files, split="train", cache_dir=model_args.cache_dir)
+    maxlen = model_args.export_quantization_maxlen
+
+    samples = []
+    for _ in range(model_args.export_quantization_nsamples):
+        while True:
+            sample_idx = random.randint(0, len(dataset) - 1)
+            sample: Dict[str, torch.Tensor] = tokenizer(dataset[sample_idx]["text"], return_tensors="pt")
+            if sample["input_ids"].size(1) >= maxlen:
+                break # TODO: fix large maxlen
+
+        word_idx = random.randint(0, sample["input_ids"].size(1) - maxlen - 1)
+        input_ids = sample["input_ids"][:, word_idx : word_idx + maxlen]
+        samples.append(tokenizer.decode(input_ids[0].tolist(), skip_special_tokens=True))
+
+    return samples
+
+
+def _configure_rope(config: "PretrainedConfig", model_args: "ModelArguments", is_trainable: bool) -> None:
+    if not hasattr(config, "rope_scaling"):
+        logger.warning("Current model does not support RoPE scaling.")
+        return
+
+    if is_trainable:
+        if model_args.rope_scaling == "dynamic":
+            logger.warning(
+                "Dynamic NTK scaling may not work well with fine-tuning. "
+                "See: https://github.com/huggingface/transformers/pull/24653"
+            )
+
+        current_max_length = getattr(config, "max_position_embeddings", None)
+        if current_max_length and model_args.model_max_length > current_max_length:
+            scaling_factor = float(math.ceil(model_args.model_max_length / current_max_length))
+        else:
+            logger.warning("Input length is smaller than max length. Consider increase input length.")
+            scaling_factor = 1.0
+    else:
+        scaling_factor = 2.0
+
+    setattr(config, "rope_scaling", {"type": model_args.rope_scaling, "factor": scaling_factor})
+    logger.info("Using {} scaling strategy and setting scaling factor to {}".format(
+        model_args.rope_scaling, scaling_factor
+    ))
+
+
+def _configure_flashattn(config_kwargs: Dict[str, Any]) -> None:
+    if not is_flash_attn2_available():
+        logger.warning("FlashAttention2 is not installed.")
+        return
+
+    config_kwargs["use_flash_attention_2"] = True
+    logger.info("Using FlashAttention-2 for faster training and inference.")
+
+
+def _configure_longlora(config: "PretrainedConfig") -> None:
+    if getattr(config, "model_type", None) in SUPPORTED_CLASS_FOR_S2ATTN:
+        setattr(config, "group_size_ratio", 0.25)
+        logger.info("Using shift short attention with group_size_ratio=1/4.")
+    else:
+        logger.warning("Current model does not support shift short attention.")
+
+
+def _configure_quantization(
+    config: "PretrainedConfig",
+    tokenizer: "PreTrainedTokenizer",
+    model_args: "ModelArguments",
+    config_kwargs: Dict[str, Any]
+) -> None:
+    r"""
+    Priority: GPTQ-quantized (training) > AutoGPTQ (export) > Bitsandbytes (training)
+    """
+    if getattr(config, "quantization_config", None): # gptq
+        if is_deepspeed_zero3_enabled():
+            raise ValueError("DeepSpeed ZeRO-3 is incompatible with quantization.")
+
+        config_kwargs["device_map"] = {"": get_current_device()}
+        quantization_config: Dict[str, Any] = getattr(config, "quantization_config", None)
+        if quantization_config.get("quant_method", None) == "gptq" and quantization_config.get("bits", -1) == 4:
+            quantization_config["use_exllama"] = False # disable exllama
+        logger.info("Loading {}-bit GPTQ-quantized model.".format(quantization_config.get("bits", -1)))
+
+    elif model_args.export_quantization_bit is not None: # auto-gptq
+        require_version("optimum>=1.16.0", "To fix: pip install optimum>=1.16.0")
+        require_version("auto_gptq>=0.5.0", "To fix: pip install auto_gptq>=0.5.0")
+        from accelerate.utils import get_max_memory
+
+        if getattr(config, "model_type", None) == "chatglm":
+            raise ValueError("ChatGLM model is not supported.")
+
+        config_kwargs["quantization_config"] = GPTQConfig(
+            bits=model_args.export_quantization_bit,
+            tokenizer=tokenizer,
+            dataset=_get_quantization_dataset(tokenizer, model_args)
+        )
+        config_kwargs["device_map"] = "auto"
+        config_kwargs["max_memory"] = get_max_memory()
+        logger.info("Quantizing model to {} bit.".format(model_args.export_quantization_bit))
+
+    elif model_args.quantization_bit is not None: # bnb
+        if is_deepspeed_zero3_enabled():
+            raise ValueError("DeepSpeed ZeRO-3 is incompatible with quantization.")
+
+        if model_args.quantization_bit == 8:
+            require_version("bitsandbytes>=0.37.0", "To fix: pip install bitsandbytes>=0.37.0")
+            config_kwargs["quantization_config"] = BitsAndBytesConfig(load_in_8bit=True)
+
+        elif model_args.quantization_bit == 4:
+            require_version("bitsandbytes>=0.39.0", "To fix: pip install bitsandbytes>=0.39.0")
+            config_kwargs["quantization_config"] = BitsAndBytesConfig(
+                load_in_4bit=True,
+                bnb_4bit_compute_dtype=model_args.compute_dtype,
+                bnb_4bit_use_double_quant=model_args.double_quantization,
+                bnb_4bit_quant_type=model_args.quantization_type
+            )
+
+        config_kwargs["device_map"] = {"": get_current_device()}
+        logger.info("Quantizing model to {} bit.".format(model_args.quantization_bit))
+
+
+def _prepare_model_for_training(
+    model: "PreTrainedModel",
+    model_args: "ModelArguments",
+    output_layer_name: Optional[str] = "lm_head"
+) -> None:
+    r"""
+    Includes:
+        (1) cast the layernorm in fp32
+        (2) make output embedding layer require grads
+        (3) add the upcasting of the lm_head in fp32
+    Inspired by: https://github.com/huggingface/peft/blob/v0.7.1/src/peft/utils/other.py#L72
+    """
+    if model_args.upcast_layernorm:
+        for name, param in model.named_parameters():
+            if param.ndim == 1 and any(ln_name in name for ln_name in LAYERNORM_NAMES):
+                param.data = param.data.to(torch.float32)
+        logger.info("Upcasting layernorm weights in float32.")
+
+    if not model_args.disable_gradient_checkpointing:
+        if not getattr(model, "supports_gradient_checkpointing", False):
+            logger.warning("Current model does not support gradient checkpointing.")
+        else:
+            model.enable_input_require_grads()
+            model.gradient_checkpointing_enable()
+            model.config.use_cache = False # turn off when gradient checkpointing is enabled
+            logger.info("Gradient checkpointing enabled.")
+
+    if hasattr(model, output_layer_name):
+        def fp32_forward_post_hook(module: torch.nn.Module, args: Tuple[torch.Tensor], output: torch.Tensor):
+            return output.to(torch.float32)
+
+        output_layer = getattr(model, output_layer_name)
+        if isinstance(output_layer, torch.nn.Linear) and output_layer.weight.dtype != torch.float32:
+            output_layer.register_forward_hook(fp32_forward_post_hook)
+
+
+def patch_tokenizer(tokenizer: "PreTrainedTokenizer") -> None:
+    if "PreTrainedTokenizerBase" not in str(tokenizer._pad.__func__):
+        tokenizer._pad = MethodType(PreTrainedTokenizerBase._pad, tokenizer)
+
+
+def patch_config(
+    config: "PretrainedConfig",
+    tokenizer: "PreTrainedTokenizer",
+    model_args: "ModelArguments",
+    config_kwargs: Dict[str, Any],
+    is_trainable: bool
+) -> None:
+    if model_args.compute_dtype is None: # priority: bf16 > fp16 > fp32
+        model_args.compute_dtype = infer_optim_dtype(model_dtype=getattr(config, "torch_dtype", None))
+
+    if getattr(config, "model_type", None) == "qwen":
+        for dtype_name, dtype in [("fp16", torch.float16), ("bf16", torch.bfloat16), ("fp32", torch.float32)]:
+            setattr(config, dtype_name, model_args.compute_dtype == dtype)
+
+    if model_args.rope_scaling is not None:
+        _configure_rope(config, model_args, is_trainable)
+
+    if model_args.flash_attn:
+        _configure_flashattn(config_kwargs)
+
+    if is_trainable and model_args.shift_attn:
+        _configure_longlora(config)
+
+    _configure_quantization(config, tokenizer, model_args, config_kwargs)
+
+
+def patch_model(
+    model: "PreTrainedModel",
+    tokenizer: "PreTrainedTokenizer",
+    model_args: "ModelArguments",
+    is_trainable: bool
+) -> None:
+    if "GenerationMixin" not in str(model.generate.__func__):
+        model.generate = MethodType(PreTrainedModel.generate, model)
+
+    if getattr(model.config, "model_type", None) == "chatglm":
+        setattr(model, "lm_head", model.transformer.output_layer)
+        setattr(model, "_keys_to_ignore_on_save", ["lm_head.weight"])
+
+    if model_args.resize_vocab:
+        if is_deepspeed_zero3_enabled():
+            raise ValueError("DeepSpeed ZeRO-3 is incompatible with vocab resizing.")
+
+        _resize_embedding_layer(model, tokenizer)
+
+    if is_trainable:
+        _prepare_model_for_training(model, model_args)
+
+
+def patch_valuehead_model(model: "AutoModelForCausalLMWithValueHead") -> None:
+    def tie_weights(self: "AutoModelForCausalLMWithValueHead") -> None:
+        if isinstance(self.pretrained_model, PreTrainedModel):
+            self.pretrained_model.tie_weights()
+
+    def get_input_embeddings(self: "AutoModelForCausalLMWithValueHead") -> torch.nn.Module:
+        if isinstance(self.pretrained_model, PreTrainedModel):
+            return self.pretrained_model.get_input_embeddings()
+
+    ignore_modules = [name for name, _ in model.named_parameters() if "pretrained_model" in name]
+    setattr(model, "_keys_to_ignore_on_save", ignore_modules)
+    setattr(model, "tie_weights", MethodType(tie_weights, model))
+    setattr(model, "get_input_embeddings", MethodType(get_input_embeddings, model))

LLM-Detector-V7-11w/src/llmtuner/model/utils.py

@@ -0,0 +1,129 @@
+import torch
+import inspect
+from typing import TYPE_CHECKING, Any, Dict, List
+from transformers import PreTrainedModel
+from transformers.utils import cached_file
+
+from llmtuner.extras.constants import V_HEAD_WEIGHTS_NAME, V_HEAD_SAFE_WEIGHTS_NAME
+from llmtuner.extras.logging import get_logger
+from llmtuner.extras.misc import get_current_device
+
+if TYPE_CHECKING:
+    from transformers import PretrainedConfig, PreTrainedTokenizer
+    from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments
+
+
+logger = get_logger(__name__)
+
+
+def dispatch_model(model: "PreTrainedModel") -> "PreTrainedModel":
+    r"""
+    Dispatches a pre-trained model to GPUs with balanced memory when the GPU is available.
+    Borrowed from: https://github.com/huggingface/transformers/blob/v4.36.2/src/transformers/modeling_utils.py#L3570
+    """
+    if getattr(model, "quantization_method", None): # already set on current device
+        return model
+
+    if (
+        torch.cuda.device_count() > 1
+        and isinstance(model, PreTrainedModel)
+        and model._no_split_modules is not None
+        and model.config.model_type != "chatglm"
+    ):
+        from accelerate import dispatch_model
+        from accelerate.utils import infer_auto_device_map, get_balanced_memory
+
+        kwargs = {"dtype": model.dtype, "no_split_module_classes": model._get_no_split_modules("auto")}
+        max_memory = get_balanced_memory(model, **kwargs)
+        # Make sure tied weights are tied before creating the device map.
+        model.tie_weights()
+        device_map = infer_auto_device_map(model, max_memory=max_memory, **kwargs)
+        device_map_kwargs = {"device_map": device_map}
+        if "skip_keys" in inspect.signature(dispatch_model).parameters:
+            device_map_kwargs["skip_keys"] = model._skip_keys_device_placement
+        return dispatch_model(model, **device_map_kwargs)
+    else:
+        return model.to(device=get_current_device())
+
+
+def find_all_linear_modules(model: "PreTrainedModel") -> List[str]:
+    r"""
+    Finds all available modules to apply lora.
+    """
+    quantization_method = getattr(model, "quantization_method", None)
+    if quantization_method is None:
+        linear_cls = torch.nn.Linear
+    elif quantization_method == "bitsandbytes":
+        import bitsandbytes as bnb
+        linear_cls = bnb.nn.Linear4bit if getattr(model, "is_loaded_in_4bit", False) else bnb.nn.Linear8bitLt
+    else:
+        raise ValueError("Finding linear modules for {} models is not supported.".format(quantization_method))
+
+    output_layer_names = ["lm_head"]
+    if model.config.model_type == "chatglm":
+        output_layer_names.append("output_layer")
+
+    module_names = set()
+    for name, module in model.named_modules():
+        if (
+            isinstance(module, linear_cls)
+            and not any([output_layer in name for output_layer in output_layer_names])
+        ):
+            module_names.add(name.split(".")[-1])
+
+    logger.info("Found linear modules: {}".format(",".join(module_names)))
+    return list(module_names)
+
+
+def get_modelcard_args(
+    model_args: "ModelArguments",
+    data_args: "DataArguments",
+    finetuning_args: "FinetuningArguments"
+) -> Dict[str, Any]:
+    return {
+        "tasks": "text-generation",
+        "license": "other",
+        "finetuned_from": model_args.model_name_or_path,
+        "dataset": [dataset.strip() for dataset in data_args.dataset.split(",")],
+        "tags": ["llama-factory"] + (["lora"] if finetuning_args.finetuning_type == "lora" else [])
+    }
+
+
+def load_valuehead_params(path_or_repo_id: str, model_args: "ModelArguments") -> Dict[str, torch.Tensor]:
+    r"""
+    Loads value head parameters from Hugging Face Hub or local disk.
+
+    Returns: dict with keys `v_head.summary.weight` and `v_head.summary.bias`.
+    """
+    kwargs = {
+        "path_or_repo_id": path_or_repo_id,
+        "cache_dir": model_args.cache_dir,
+        "token": model_args.hf_hub_token
+    }
+
+    try:
+        from safetensors import safe_open
+        vhead_file = cached_file(filename=V_HEAD_SAFE_WEIGHTS_NAME, **kwargs)
+        with safe_open(vhead_file, framework="pt", device="cpu") as f:
+            return {key: f.get_tensor(key) for key in f.keys()}
+    except Exception as err:
+        logger.info("Failed to load {}: {}".format(V_HEAD_SAFE_WEIGHTS_NAME, str(err)))
+
+    try:
+        vhead_file = cached_file(filename=V_HEAD_WEIGHTS_NAME, **kwargs)
+        return torch.load(vhead_file, map_location="cpu")
+    except Exception as err:
+        logger.info("Failed to load {}: {}".format(V_HEAD_WEIGHTS_NAME, str(err)))
+
+    logger.info("Provided path ({}) does not contain value head weights.".format(path_or_repo_id))
+    logger.info("Ignore these messages if you are not resuming the training of a value head model.")
+    return None
+
+
+def register_autoclass(config: "PretrainedConfig", model: "PreTrainedModel", tokenizer: "PreTrainedTokenizer"):
+    if "AutoConfig" in getattr(config, "auto_map", {}):
+        config.__class__.register_for_auto_class()
+    if "AutoModelForCausalLM" in getattr(config, "auto_map", {}):
+        model.__class__.register_for_auto_class()
+    if "AutoTokenizer" in tokenizer.init_kwargs.get("auto_map", {}):
+        tokenizer.__class__.register_for_auto_class()

LLM-Detector-V7-11w/src/llmtuner/train/__init__.py

@@ -0,0 +1 @@
+from llmtuner.train.tuner import export_model, run_exp

LLM-Detector-V7-11w/src/llmtuner/train/dpo/__init__.py

@@ -0,0 +1 @@
+from llmtuner.train.dpo.workflow import run_dpo

LLM-Detector-V7-11w/src/llmtuner/train/dpo/collator.py

@@ -0,0 +1,51 @@
+import torch
+from dataclasses import dataclass
+from typing import Any, Dict, List, Sequence, Tuple
+from transformers import DataCollatorForSeq2Seq
+
+
+@dataclass
+class DPODataCollatorWithPadding(DataCollatorForSeq2Seq):
+    r"""
+    Data collator for pairwise data.
+    """
+
+    def _pad_labels(self, batch: torch.Tensor, positions: List[Tuple[int, int]]) -> torch.Tensor:
+        padded_labels = []
+        for feature, (prompt_len, answer_len) in zip(batch, positions):
+            if self.tokenizer.padding_side == "left":
+                start, end = feature.size(0) - answer_len, feature.size(0)
+            else:
+                start, end = prompt_len, prompt_len + answer_len
+            padded_tensor = self.label_pad_token_id * torch.ones_like(feature)
+            padded_tensor[start:end] = feature[start:end]
+            padded_labels.append(padded_tensor)
+        return torch.stack(padded_labels, dim=0).contiguous() # in contiguous memory
+
+    def __call__(self, features: Sequence[Dict[str, Any]]) -> Dict[str, torch.Tensor]:
+        r"""
+        Pads batched data to the longest sequence in the batch.
+
+        We generate 2 * n examples where the first n examples represent chosen examples and
+        the last n examples represent rejected examples.
+        """
+        concatenated_features = []
+        label_positions = []
+        for key in ("chosen_ids", "rejected_ids"):
+            for feature in features:
+                prompt_len, answer_len = len(feature["prompt_ids"]), len(feature[key])
+                concatenated_features.append({
+                    "input_ids": feature["prompt_ids"] + feature[key],
+                    "attention_mask": [1] * (prompt_len + answer_len)
+                })
+                label_positions.append((prompt_len, answer_len))
+
+        batch = self.tokenizer.pad(
+            concatenated_features,
+            padding=self.padding,
+            max_length=self.max_length,
+            pad_to_multiple_of=self.pad_to_multiple_of,
+            return_tensors=self.return_tensors,
+        )
+        batch["labels"] = self._pad_labels(batch["input_ids"], label_positions)
+        return batch

LLM-Detector-V7-11w/src/llmtuner/train/dpo/trainer.py

@@ -0,0 +1,159 @@
+import torch
+from collections import defaultdict
+from typing import TYPE_CHECKING, Dict, Literal, Optional, Tuple, Union
+from transformers import BatchEncoding, Trainer
+from trl import DPOTrainer
+from trl.trainer.utils import disable_dropout_in_model
+
+from llmtuner.extras.constants import IGNORE_INDEX
+
+if TYPE_CHECKING:
+    from transformers import PreTrainedModel
+
+
+class CustomDPOTrainer(DPOTrainer):
+
+    def __init__(
+        self,
+        beta: float,
+        loss_type: Literal["sigmoid", "hinge", "ipo", "kto"],
+        ftx_gamma: float,
+        model: Union["PreTrainedModel", torch.nn.Module],
+        ref_model: Optional[Union["PreTrainedModel", torch.nn.Module]] = None,
+        disable_dropout: Optional[bool] = True,
+        **kwargs
+    ):
+        if disable_dropout:
+            disable_dropout_in_model(model)
+            if ref_model is not None:
+                disable_dropout_in_model(ref_model)
+
+        self.use_dpo_data_collator = True # hack to avoid warning
+        self.generate_during_eval = False # disable at evaluation
+        self.label_pad_token_id = IGNORE_INDEX
+        self.padding_value = 0
+        self.is_encoder_decoder = model.config.is_encoder_decoder
+        self.precompute_ref_log_probs = False
+        self._precomputed_train_ref_log_probs = False
+        self._precomputed_eval_ref_log_probs = False
+        self._peft_has_been_casted_to_bf16 = False
+
+        self.ref_model = ref_model
+        self.beta = beta
+        self.label_smoothing = 0
+        self.loss_type = loss_type
+        self.ftx_gamma = ftx_gamma
+        self._stored_metrics = defaultdict(lambda: defaultdict(list))
+
+        Trainer.__init__(self, model=model, **kwargs)
+        if not hasattr(self, "accelerator"):
+            raise AttributeError("Please update `transformers`.")
+
+        if ref_model is not None:
+            if self.is_deepspeed_enabled:
+                if not (
+                    getattr(ref_model, "is_loaded_in_8bit", False)
+                    or getattr(ref_model, "is_loaded_in_4bit", False)
+                ): # quantized models are already set on the correct device
+                    self.ref_model = self._prepare_deepspeed(self.ref_model)
+            else:
+                self.ref_model = self.accelerator.prepare_model(self.ref_model, evaluation_mode=True)
+
+    def sft_loss(
+        self,
+        chosen_logits: torch.FloatTensor,
+        chosen_labels: torch.LongTensor
+    ) -> torch.Tensor:
+        r"""
+        Computes supervised cross-entropy loss of given labels under the given logits.
+
+        Returns:
+            A tensor of shape (batch_size,) containing the cross-entropy loss of each samples.
+        """
+        all_logps = self.get_batch_logps(
+            chosen_logits,
+            chosen_labels,
+            average_log_prob=True
+        )
+        return -all_logps
+
+    def concatenated_forward(
+        self,
+        model: "PreTrainedModel",
+        batch: Dict[str, torch.Tensor]
+    ) -> Tuple[torch.FloatTensor, torch.FloatTensor, torch.FloatTensor, torch.FloatTensor]:
+        batch_copied = BatchEncoding({k: v.detach().clone() for k, v in batch.items()}) # avoid error
+
+        all_logits = model(
+            input_ids=batch_copied["input_ids"],
+            attention_mask=batch_copied["attention_mask"],
+            return_dict=True
+        ).logits.to(torch.float32)
+
+        all_logps = self.get_batch_logps(
+            all_logits,
+            batch["labels"],
+            average_log_prob=False
+        )
+        batch_size = batch["input_ids"].size(0) // 2
+        chosen_logps, rejected_logps = all_logps.split(batch_size, dim=0)
+        chosen_logits, rejected_logits = all_logits.split(batch_size, dim=0)
+        return chosen_logps, rejected_logps, chosen_logits, rejected_logits
+
+    def get_batch_loss_metrics(
+        self,
+        model: "PreTrainedModel",
+        batch: Dict[str, torch.Tensor],
+        train_eval: Optional[Literal["train", "eval"]] = "train"
+    ) -> Tuple[torch.Tensor, Dict[str, torch.Tensor]]:
+        r"""
+        Computes the DPO loss and other metrics for the given batch of inputs for train or test.
+        """
+        metrics = {}
+        (
+            policy_chosen_logps,
+            policy_rejected_logps,
+            policy_chosen_logits,
+            policy_rejected_logits,
+        ) = self.concatenated_forward(model, batch)
+        with torch.no_grad():
+            if self.ref_model is None:
+                with self.accelerator.unwrap_model(self.model).disable_adapter():
+                    (
+                        reference_chosen_logps,
+                        reference_rejected_logps,
+                        _,
+                        _,
+                    ) = self.concatenated_forward(self.model, batch)
+            else:
+                (
+                    reference_chosen_logps,
+                    reference_rejected_logps,
+                    _,
+                    _,
+                ) = self.concatenated_forward(self.ref_model, batch)
+
+        losses, chosen_rewards, rejected_rewards = self.dpo_loss(
+            policy_chosen_logps,
+            policy_rejected_logps,
+            reference_chosen_logps,
+            reference_rejected_logps,
+        )
+        if self.ftx_gamma > 1e-6:
+            batch_size = batch["input_ids"].size(0) // 2
+            chosen_labels, _ = batch["labels"].split(batch_size, dim=0)
+            losses += self.ftx_gamma * self.sft_loss(policy_chosen_logits, chosen_labels)
+
+        reward_accuracies = (chosen_rewards > rejected_rewards).float()
+
+        prefix = "eval_" if train_eval == "eval" else ""
+        metrics[f"{prefix}rewards/chosen"] = chosen_rewards.cpu().mean()
+        metrics[f"{prefix}rewards/rejected"] = rejected_rewards.cpu().mean()
+        metrics[f"{prefix}rewards/accuracies"] = reward_accuracies.cpu().mean()
+        metrics[f"{prefix}rewards/margins"] = (chosen_rewards - rejected_rewards).cpu().mean()
+        metrics[f"{prefix}logps/rejected"] = policy_rejected_logps.detach().cpu().mean()
+        metrics[f"{prefix}logps/chosen"] = policy_chosen_logps.detach().cpu().mean()
+        metrics[f"{prefix}logits/rejected"] = policy_rejected_logits.detach().cpu().mean()
+        metrics[f"{prefix}logits/chosen"] = policy_chosen_logits.detach().cpu().mean()
+
+        return losses.mean(), metrics

LLM-Detector-V7-11w/src/llmtuner/train/dpo/workflow.py

@@ -0,0 +1,82 @@
+# Inspired by: https://github.com/huggingface/trl/blob/main/examples/research_projects/stack_llama_2/scripts/dpo_llama2.py
+
+from typing import TYPE_CHECKING, Optional, List
+from transformers import Seq2SeqTrainingArguments
+
+from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
+from llmtuner.extras.constants import IGNORE_INDEX
+from llmtuner.extras.ploting import plot_loss
+from llmtuner.hparams import ModelArguments
+from llmtuner.model import load_model_and_tokenizer
+from llmtuner.train.dpo.collator import DPODataCollatorWithPadding
+from llmtuner.train.dpo.trainer import CustomDPOTrainer
+from llmtuner.train.utils import create_modelcard_and_push, create_ref_model
+
+if TYPE_CHECKING:
+    from transformers import TrainerCallback
+    from llmtuner.hparams import DataArguments, FinetuningArguments
+
+
+def run_dpo(
+    model_args: "ModelArguments",
+    data_args: "DataArguments",
+    training_args: "Seq2SeqTrainingArguments",
+    finetuning_args: "FinetuningArguments",
+    callbacks: Optional[List["TrainerCallback"]] = None
+):
+    dataset = get_dataset(model_args, data_args)
+    model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train)
+    dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="rm")
+    data_collator = DPODataCollatorWithPadding(
+        tokenizer=tokenizer,
+        pad_to_multiple_of=8,
+        label_pad_token_id=IGNORE_INDEX if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
+    )
+
+    # Create reference model
+    if finetuning_args.ref_model is None and (not training_args.do_train): # use the model itself
+        ref_model = model
+    else:
+        ref_model = create_ref_model(model_args, finetuning_args)
+
+    # Update arguments
+    training_args_dict = training_args.to_dict()
+    training_args_dict.update(dict(remove_unused_columns=False)) # important for pairwise dataset
+    training_args = Seq2SeqTrainingArguments(**training_args_dict)
+
+    # Initialize our Trainer
+    trainer = CustomDPOTrainer(
+        beta=finetuning_args.dpo_beta,
+        loss_type=finetuning_args.dpo_loss,
+        ftx_gamma=finetuning_args.dpo_ftx,
+        model=model,
+        ref_model=ref_model,
+        args=training_args,
+        tokenizer=tokenizer,
+        data_collator=data_collator,
+        callbacks=callbacks,
+        **split_dataset(dataset, data_args, training_args)
+    )
+
+    # Training
+    if training_args.do_train:
+        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
+        trainer.save_model()
+        trainer.log_metrics("train", train_result.metrics)
+        trainer.save_metrics("train", train_result.metrics)
+        trainer.save_state()
+        if trainer.is_world_process_zero() and finetuning_args.plot_loss:
+            plot_loss(training_args.output_dir, keys=["loss", "eval_loss"])
+
+    # Evaluation
+    if training_args.do_eval:
+        metrics = trainer.evaluate(metric_key_prefix="eval")
+        if id(model) == id(ref_model): # unable to compute rewards without a reference model
+            remove_keys = [key for key in metrics.keys() if "rewards" in key]
+            for key in remove_keys:
+                metrics.pop(key)
+        trainer.log_metrics("eval", metrics)
+        trainer.save_metrics("eval", metrics)
+
+    # Create model card
+    create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)

LLM-Detector-V7-11w/src/llmtuner/train/ppo/__init__.py

@@ -0,0 +1 @@
+from llmtuner.train.ppo.workflow import run_ppo

LLM-Detector-V7-11w/src/llmtuner/train/ppo/trainer.py

@@ -0,0 +1,374 @@
+import os
+import sys
+import math
+import torch
+from tqdm import tqdm
+from typing import TYPE_CHECKING, Dict, List, Optional, Tuple
+
+from transformers import GenerationConfig, Trainer, TrainerState, TrainerControl
+from transformers.utils import WEIGHTS_NAME, SAFE_WEIGHTS_NAME
+from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR
+from transformers.trainer_pt_utils import remove_dummy_checkpoint
+
+from trl import PPOTrainer
+from trl.core import PPODecorators, logprobs_from_logits
+
+from llmtuner.extras.callbacks import LogCallback, FixValueHeadModelCallback
+from llmtuner.extras.logging import get_logger
+from llmtuner.extras.misc import AverageMeter, count_parameters, get_logits_processor
+from llmtuner.train.ppo.utils import dump_layernorm, get_rewards_from_server, restore_layernorm, replace_model
+
+if TYPE_CHECKING:
+    from transformers import Seq2SeqTrainingArguments, TrainerCallback
+    from trl import AutoModelForCausalLMWithValueHead
+    from llmtuner.hparams import ModelArguments, FinetuningArguments, GeneratingArguments
+
+
+logger = get_logger(__name__)
+
+
+class CustomPPOTrainer(PPOTrainer, Trainer):
+    r"""
+    Inherits PPOTrainer.
+    """
+
+    def __init__(
+        self,
+        model_args: "ModelArguments",
+        training_args: "Seq2SeqTrainingArguments",
+        finetuning_args: "FinetuningArguments",
+        generating_args: "GeneratingArguments",
+        callbacks: List["TrainerCallback"],
+        reward_model: "AutoModelForCausalLMWithValueHead",
+        **kwargs
+    ):
+        PPOTrainer.__init__(self, **kwargs)
+
+        self.args = training_args
+        self.model_args = model_args
+        self.finetuning_args = finetuning_args
+        self.reward_model = reward_model
+
+        self.generation_config = GenerationConfig(
+            pad_token_id=self.tokenizer.pad_token_id,
+            eos_token_id=[self.tokenizer.eos_token_id] + self.tokenizer.additional_special_tokens_ids,
+            **generating_args.to_dict()
+        )
+
+        self.state = TrainerState()
+        self.control = TrainerControl()
+        self.is_deepspeed_enabled = self.accelerator.distributed_type == "DEEPSPEED" and hasattr(
+            self.accelerator.state, "deepspeed_plugin"
+        )
+        self.log_callback, self.save_callback = callbacks[0], callbacks[1]
+        assert isinstance(self.log_callback, LogCallback) and isinstance(self.save_callback, FixValueHeadModelCallback)
+
+        if self.args.max_steps > 0:
+            logger.info("max_steps is given, it will override any value given in num_train_epochs")
+
+        if finetuning_args.reward_model_type == "full":
+            if self.is_deepspeed_enabled:
+                if not (
+                    getattr(reward_model.pretrained_model, "is_loaded_in_8bit", False)
+                    or getattr(reward_model.pretrained_model, "is_loaded_in_4bit", False)
+                ): # quantized models are already set on the correct device
+                    self.reward_model = self._prepare_deepspeed(self.reward_model)
+            else:
+                self.reward_model = self.accelerator.prepare_model(self.reward_model, evaluation_mode=True)
+
+    def ppo_train(self, resume_from_checkpoint: Optional[str] = None) -> None:
+        r"""
+        Implements training loop for the PPO stage, like _inner_training_loop() in Huggingface's Trainer.
+        """
+        if resume_from_checkpoint is not None:
+            raise ValueError("`resume_from_checkpoint` will be supported in the future version.")
+
+        total_train_batch_size = (
+            self.args.per_device_train_batch_size
+            * self.args.gradient_accumulation_steps
+            * self.finetuning_args.ppo_buffer_size
+            * self.args.world_size
+        )
+        if self.args.max_steps > 0:
+            num_examples = total_train_batch_size * self.args.max_steps
+            num_train_epochs = sys.maxsize
+            max_steps = self.args.max_steps
+            steps_in_epoch = self.args.max_steps
+        else:
+            len_dataloader = len(self.dataloader)
+            num_examples = len(self.dataset)
+            num_train_epochs = self.args.num_train_epochs
+            max_steps = math.ceil(num_train_epochs * len_dataloader)
+            steps_in_epoch = len_dataloader
+
+        self.state.max_steps = max_steps
+        self.state.num_train_epochs = num_train_epochs
+        self.state.is_local_process_zero = self.is_local_process_zero()
+        self.state.is_world_process_zero = self.is_world_process_zero()
+
+        if self.is_world_process_zero():
+            logger.info("***** Running training *****")
+            logger.info("  Num examples = {}".format(num_examples))
+            logger.info("  Num Epochs = {}".format(num_train_epochs))
+            logger.info("  Instantaneous batch size per device = {}".format(self.args.per_device_train_batch_size))
+            logger.info("  Total train batch size (w. parallel, buffer, distributed & accumulation) = {}".format(
+                total_train_batch_size
+            ))
+            logger.info("  Gradient Accumulation steps = {}".format(self.args.gradient_accumulation_steps))
+            logger.info("  Num optimization epochs per batch = {}".format(self.finetuning_args.ppo_epochs))
+            logger.info("  Total training steps = {}".format(max_steps))
+            logger.info("  Number of trainable parameters = {}".format(count_parameters(self.model)[0]))
+
+        unwrapped_model: "AutoModelForCausalLMWithValueHead" = self.accelerator.unwrap_model(self.model)
+        dataiter = iter(self.dataloader)
+        loss_meter = AverageMeter()
+        reward_meter = AverageMeter()
+        self.log_callback.on_train_begin(self.args, self.state, self.control)
+
+        for step in tqdm(range(max_steps), disable=not self.is_local_process_zero()):
+            try:
+                batch = next(dataiter)
+            except StopIteration:
+                dataiter = iter(self.dataloader)
+                batch = next(dataiter)
+
+            # Cast to inference mode
+            unwrapped_model.gradient_checkpointing_disable()
+            unwrapped_model.config.use_cache = True
+            self.model.eval()
+
+            # Get inputs
+            self.tokenizer.padding_side = "right" # change padding side
+            queries, responses, rewards = [], [], []
+            for idx in range(0, self.config.batch_size, self.config.mini_batch_size):
+                mini_batch_queries, mini_batch_responses = self.get_inputs(batch[idx:idx+self.config.mini_batch_size])
+                mini_batch_rewards = self.get_rewards(mini_batch_queries, mini_batch_responses, unwrapped_model)
+                queries.extend(mini_batch_queries)
+                responses.extend(mini_batch_responses)
+                rewards.extend(mini_batch_rewards)
+
+            # Cast to training mode
+            unwrapped_model.gradient_checkpointing_enable()
+            unwrapped_model.config.use_cache = False
+            self.model.train()
+
+            # Run PPO step
+            stats = self.step(queries, responses, rewards)
+            self.tokenizer.padding_side = "left" # restore padding side
+            loss_meter.update(float(stats["ppo/loss/total"]), n=len(rewards))
+            reward_meter.update(torch.stack(rewards).mean().item(), n=len(rewards))
+
+            if self.config.log_with is not None:
+                try:
+                    batch["query"] = self.tokenizer.batch_decode(queries, skip_special_tokens=True)
+                    batch["response"] = self.tokenizer.batch_decode(responses, skip_special_tokens=True)
+                    self.log_stats(stats, batch, rewards)
+                except:
+                    logger.warning("Failed to save stats due to unknown errors.")
+
+            self.state.global_step += 1
+            self.log_callback.on_step_end(self.args, self.state, self.control)
+
+            if self.is_local_process_zero() and (step+1) % self.args.logging_steps == 0:
+                logs = dict(
+                    loss=round(loss_meter.avg, 4),
+                    reward=round(reward_meter.avg, 4),
+                    learning_rate=stats["ppo/learning_rate"],
+                    epoch=round(step / steps_in_epoch, 2)
+                )
+                tqdm.write(str(logs))
+                logs["step"] = step
+                self.state.log_history.append(logs)
+                self.log_callback.on_log(self.args, self.state, self.control)
+                loss_meter.reset()
+                reward_meter.reset()
+
+            if (step+1) % self.args.save_steps == 0: # save checkpoint
+                self.save_model(os.path.join(
+                    self.args.output_dir, "{}-{}".format(PREFIX_CHECKPOINT_DIR, self.state.global_step)
+                ))
+                self.save_callback.on_save(
+                    self.args, self.state, self.control, model=self.accelerator.unwrap_model(self.model)
+                )
+
+            if self.control.should_epoch_stop or self.control.should_training_stop:
+                break
+
+        self.log_callback.on_train_end(self.args, self.state, self.control)
+        self.save_callback.on_train_end(
+            self.args, self.state, self.control, model=self.accelerator.unwrap_model(self.model)
+        )
+
+    @torch.no_grad()
+    def get_inputs(self, batch: Dict[str, torch.Tensor]) -> Tuple[List[torch.Tensor], List[torch.Tensor]]:
+        r"""
+        Generates model's responses given queries.
+        """
+        if self.model_args.upcast_layernorm:
+            layernorm_params = dump_layernorm(self.model)
+
+        if batch["input_ids"].size(0) == 1: # handle llama2 ppo with gradient accumulation > 1
+            start_index = (batch["input_ids"][0] != self.tokenizer.pad_token_id).nonzero()[0].item()
+            for k, v in batch.items():
+                batch[k] = v[:, start_index:]
+
+        unwrapped_model: "AutoModelForCausalLMWithValueHead" = self.accelerator.unwrap_model(self.model)
+        generate_output: torch.Tensor = unwrapped_model.generate(
+            generation_config=self.generation_config,
+            logits_processor=get_logits_processor(),
+            **batch
+        )
+
+        if self.model_args.upcast_layernorm:
+            restore_layernorm(self.model, layernorm_params)
+
+        query = batch["input_ids"].detach().cpu()
+        response = generate_output[:, batch["input_ids"].size(-1):].detach().cpu()
+        queries, responses = [], []
+        for i in range(len(query)):
+            query_start_index = (query[i] != self.tokenizer.pad_token_id).nonzero()[0].item()
+            response_index = (response[i] != self.tokenizer.pad_token_id).nonzero()
+
+            if len(response_index) == 0:
+                response_length = 1 # allow empty response
+            else:
+                response_length = response_index[-1].item() + 1
+
+            queries.append(query[i, query_start_index:]) # remove padding from left
+            responses.append(response[i, :response_length]) # remove padding from right
+
+        return queries, responses
+
+    @torch.no_grad()
+    def get_rewards(
+        self,
+        queries: List[torch.Tensor],
+        responses: List[torch.Tensor],
+        unwrapped_model: "AutoModelForCausalLMWithValueHead"
+    ) -> List[torch.Tensor]:
+        r"""
+        Computes scores using given reward model.
+
+        Both inputs and outputs are put on CPU.
+        """
+        if self.finetuning_args.reward_model_type == "api":
+            token_ids = [torch.cat((q, r), dim=-1).tolist() for q, r in zip(queries, responses)]
+            messages = self.tokenizer.batch_decode(token_ids, skip_special_tokens=True)
+            return get_rewards_from_server(self.reward_model, messages)
+
+        if self.finetuning_args.reward_model_type == "lora":
+            replace_model(unwrapped_model, target="reward")
+            reward_model = self.model
+        else:
+            reward_model = self.reward_model
+
+        batch = self.prepare_model_inputs(queries, responses)
+
+        with torch.cuda.amp.autocast(dtype=self.model_args.compute_dtype): # support bf16
+            _, _, values = reward_model(**batch, output_hidden_states=True, return_dict=True)
+
+        if getattr(unwrapped_model.config, "model_type", None) == "chatglm": # assume same architecture
+            values = torch.transpose(values, 0, 1)
+
+        rewards = []
+        for i in range(values.size(0)):
+            end_indexes = (batch["input_ids"][i] != self.tokenizer.pad_token_id).nonzero()
+            end_index = end_indexes[-1].item() if len(end_indexes) else 0
+            rewards.append(values[i, end_index].float().detach().cpu()) # use fp32 type
+
+        if self.finetuning_args.reward_model_type == "lora":
+            replace_model(unwrapped_model, target="default")
+
+        return rewards
+
+    @PPODecorators.empty_device_cache()
+    def batched_forward_pass(
+        self,
+        model: "AutoModelForCausalLMWithValueHead",
+        queries: torch.Tensor,
+        responses: torch.Tensor,
+        model_inputs: dict,
+        return_logits: Optional[bool] = False,
+        response_masks: Optional[torch.Tensor] = None
+    ):
+        r"""
+        Calculates model outputs in multiple batches.
+
+        Subclass and override to inject custom behavior.
+        """
+        bs = len(queries)
+        fbs = self.config.mini_batch_size
+        all_logprobs = []
+        all_logits = []
+        all_masks = []
+        all_values = []
+
+        for i in range(math.ceil(bs / fbs)):
+            input_kwargs = {key: value[i * fbs : (i + 1) * fbs] for key, value in model_inputs.items()}
+            query_batch = queries[i * fbs : (i + 1) * fbs]
+            response_batch = responses[i * fbs : (i + 1) * fbs]
+            if response_masks is not None:
+                response_masks_batch = response_masks[i * fbs : (i + 1) * fbs]
+            input_ids = input_kwargs["input_ids"]
+            attention_mask = input_kwargs["attention_mask"]
+
+            with torch.cuda.amp.autocast(dtype=self.model_args.compute_dtype): # support bf16
+                logits, _, values = model(**input_kwargs)
+
+            unwrapped_model: "AutoModelForCausalLMWithValueHead" = self.accelerator.unwrap_model(self.model)
+            if getattr(unwrapped_model.config, "model_type", None) == "chatglm":
+                values = torch.transpose(values, 0, 1)
+
+            logprobs = logprobs_from_logits(logits[:, :-1, :], input_ids[:, 1:])
+            masks = torch.zeros_like(attention_mask)
+            masks[:, :-1] = attention_mask[:, 1:]
+
+            for j in range(len(query_batch)):
+                start = len(query_batch[j]) - 1
+                if attention_mask[j, 0] == 0: # offset left padding
+                    start += attention_mask[j, :].nonzero()[0].item()
+                end = start + len(response_batch[j])
+
+                if response_masks is not None:
+                    response_masks_batch = torch.cat(
+                        (torch.zeros_like(query_batch[j]), response_masks_batch[j])
+                    )[1:]
+
+                masks[j, :start] = 0
+                masks[j, end:] = 0
+                if response_masks is not None:
+                    masks[j, start:end] = masks[j, start:end] * response_masks_batch[j][start:end]
+
+            if return_logits:
+                all_logits.append(logits)
+            else:
+                del logits
+
+            all_values.append(values)
+            all_logprobs.append(logprobs)
+            all_masks.append(masks)
+
+        return (
+            torch.cat(all_logprobs),
+            torch.cat(all_logits)[:, :-1] if return_logits else None,
+            torch.cat(all_values)[:, :-1],
+            torch.cat(all_masks)[:, :-1],
+        )
+
+    def save_model(self, output_dir: Optional[str] = None) -> None:
+        r"""
+        Saves model checkpoint.
+
+        Subclass and override to inject custom behavior.
+        """
+        if self.args.should_save:
+            try:
+                self._save(output_dir, state_dict=self.accelerator.get_state_dict(self.model))
+            except ValueError:
+                logger.warning(
+                    " stage3_gather_16bit_weights_on_model_save=false. Saving the full checkpoint instead,"
+                    " use zero_to_fp32.py to recover weights"
+                )
+                self._save(output_dir, state_dict={})
+                remove_dummy_checkpoint(True, output_dir, [WEIGHTS_NAME, SAFE_WEIGHTS_NAME])
+                self.model.save_checkpoint(output_dir)

LLM-Detector-V7-11w/src/llmtuner/train/ppo/utils.py

@@ -0,0 +1,49 @@
+import json
+import torch
+from typing import TYPE_CHECKING, Dict, List, Literal, Optional
+
+from llmtuner.extras.packages import is_requests_available
+
+if TYPE_CHECKING:
+    from transformers import PreTrainedModel
+    from trl import AutoModelForCausalLMWithValueHead
+
+if is_requests_available():
+    import requests
+
+
+def get_rewards_from_server(server_url: str, messages: List[str]) -> List[torch.Tensor]:
+    headers = {"Content-Type": "application/json"}
+    payload = {"model": "model", "messages": messages}
+    response = requests.post(server_url, json=payload, headers=headers)
+    rewards = json.loads(response.text)["scores"]
+    return torch.Tensor(rewards)
+
+
+def replace_model(model: "AutoModelForCausalLMWithValueHead", target: Literal["default", "reward"]) -> None:
+    if target == "reward": # save default head temporarily
+        valuehead_state_dict: Dict[str, torch.Tensor] = model.v_head.state_dict()
+        setattr(model, "default_head_weight", valuehead_state_dict["summary.weight"].detach().clone())
+        setattr(model, "default_head_bias", valuehead_state_dict["summary.bias"].detach().clone())
+
+    model.pretrained_model.set_adapter(target) # set the LoRA adapter to be active
+    model.v_head.load_state_dict({
+        "summary.weight": model.get_buffer("{}_head_weight".format(target)).detach().clone(),
+        "summary.bias": model.get_buffer("{}_head_bias".format(target)).detach().clone()
+    })
+
+
+def dump_layernorm(model: "PreTrainedModel") -> Dict[str, torch.Tensor]:
+    layer_norm_params = {}
+    for name, param in model.named_parameters():
+        if param.data.dtype == torch.float32:
+            layer_norm_params[name] = param.data.detach().clone()
+            param.data = param.data.to(model.config.torch_dtype)
+
+    return layer_norm_params
+
+
+def restore_layernorm(model: "PreTrainedModel", layernorm_params: Optional[Dict[str, torch.Tensor]] = None) -> None:
+    for name, param in model.named_parameters():
+        if name in layernorm_params:
+            param.data = layernorm_params[name]

LLM-Detector-V7-11w/src/llmtuner/train/ppo/workflow.py

@@ -0,0 +1,103 @@
+# Inspired by: https://github.com/lvwerra/trl/blob/main/examples/research_projects/stack_llama/scripts/rl_training.py
+
+import math
+from trl import PPOConfig
+from torch.optim import AdamW
+from typing import TYPE_CHECKING, Optional, List
+from transformers import DataCollatorWithPadding
+from transformers.optimization import get_scheduler
+
+from llmtuner.data import get_dataset, preprocess_dataset
+from llmtuner.extras.callbacks import FixValueHeadModelCallback
+from llmtuner.extras.misc import fix_valuehead_checkpoint
+from llmtuner.extras.ploting import plot_loss
+from llmtuner.model import load_model_and_tokenizer
+from llmtuner.train.utils import create_ref_model, create_reward_model
+from llmtuner.train.ppo.trainer import CustomPPOTrainer
+
+if TYPE_CHECKING:
+    from transformers import Seq2SeqTrainingArguments, TrainerCallback
+    from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments, GeneratingArguments
+
+
+def run_ppo(
+    model_args: "ModelArguments",
+    data_args: "DataArguments",
+    training_args: "Seq2SeqTrainingArguments",
+    finetuning_args: "FinetuningArguments",
+    generating_args: "GeneratingArguments",
+    callbacks: Optional[List["TrainerCallback"]] = None
+):
+    dataset = get_dataset(model_args, data_args)
+    model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, add_valuehead=True)
+    dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="ppo")
+
+    tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training
+    data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
+
+    # Create reference model and reward model
+    ref_model = create_ref_model(model_args, finetuning_args, add_valuehead=True)
+    reward_model = create_reward_model(model, model_args, finetuning_args)
+
+    # Create ppo config
+    backward_batch_size = training_args.per_device_train_batch_size * training_args.gradient_accumulation_steps
+    ppo_config = PPOConfig(
+        model_name=model_args.model_name_or_path,
+        learning_rate=training_args.learning_rate,
+        mini_batch_size=training_args.per_device_train_batch_size,
+        batch_size=backward_batch_size * finetuning_args.ppo_buffer_size,
+        gradient_accumulation_steps=training_args.gradient_accumulation_steps,
+        ppo_epochs=finetuning_args.ppo_epochs,
+        max_grad_norm=training_args.max_grad_norm,
+        seed=training_args.seed,
+        optimize_device_cache=True,
+        target=finetuning_args.ppo_target,
+        log_with=finetuning_args.ppo_logger,
+        use_score_scaling=finetuning_args.ppo_score_norm,
+        use_score_norm=finetuning_args.ppo_score_norm,
+        whiten_rewards=finetuning_args.ppo_whiten_rewards,
+        accelerator_kwargs={"step_scheduler_with_optimizer": False}
+    )
+
+    # Create optimizer and scheduler
+    optimizer = AdamW(filter(lambda p: p.requires_grad, model.parameters()), lr=training_args.learning_rate)
+    if training_args.max_steps > 0:
+        num_training_steps = training_args.max_steps
+    else:
+        total_train_batch_size = backward_batch_size * finetuning_args.ppo_buffer_size * training_args.world_size
+        num_training_steps = training_args.num_train_epochs * math.ceil(len(dataset) / total_train_batch_size)
+
+    lr_scheduler = get_scheduler(
+        training_args.lr_scheduler_type,
+        optimizer=optimizer,
+        num_warmup_steps=training_args.get_warmup_steps(num_training_steps),
+        num_training_steps=num_training_steps
+    )
+
+    # Initialize our Trainer
+    ppo_trainer = CustomPPOTrainer(
+        model_args=model_args,
+        training_args=training_args,
+        finetuning_args=finetuning_args,
+        generating_args=generating_args,
+        callbacks=callbacks + [FixValueHeadModelCallback()],
+        reward_model=reward_model,
+        config=ppo_config,
+        model=model,
+        ref_model=ref_model,
+        tokenizer=tokenizer,
+        dataset=dataset,
+        data_collator=data_collator,
+        optimizer=optimizer,
+        lr_scheduler=lr_scheduler
+    )
+
+    # Training
+    if training_args.do_train:
+        ppo_trainer.ppo_train(resume_from_checkpoint=training_args.resume_from_checkpoint)
+        ppo_trainer.save_model()
+        if training_args.should_save:
+            fix_valuehead_checkpoint(model, training_args.output_dir, training_args.save_safetensors)
+        ppo_trainer.save_state() # must be called after save_model to have a folder
+        if ppo_trainer.is_world_process_zero() and finetuning_args.plot_loss:
+            plot_loss(training_args.output_dir, keys=["loss", "reward"])

LLM-Detector-V7-11w/src/llmtuner/train/pt/__init__.py

@@ -0,0 +1 @@
+from llmtuner.train.pt.workflow import run_pt

LLM-Detector-V7-11w/src/llmtuner/train/pt/workflow.py

@@ -0,0 +1,62 @@
+# Inspired by: https://github.com/huggingface/transformers/blob/v4.34.1/examples/pytorch/language-modeling/run_clm.py
+
+import math
+from typing import TYPE_CHECKING, Optional, List
+from transformers import DataCollatorForLanguageModeling, Trainer
+
+from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
+from llmtuner.extras.ploting import plot_loss
+from llmtuner.model import load_model_and_tokenizer
+from llmtuner.train.utils import create_modelcard_and_push
+
+if TYPE_CHECKING:
+    from transformers import Seq2SeqTrainingArguments, TrainerCallback
+    from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments
+
+
+def run_pt(
+    model_args: "ModelArguments",
+    data_args: "DataArguments",
+    training_args: "Seq2SeqTrainingArguments",
+    finetuning_args: "FinetuningArguments",
+    callbacks: Optional[List["TrainerCallback"]] = None
+):
+    dataset = get_dataset(model_args, data_args)
+    model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train)
+    dataset = preprocess_dataset(dataset, tokenizer, data_args, training_args, stage="pt")
+    data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
+
+    # Initialize our Trainer
+    trainer = Trainer(
+        model=model,
+        args=training_args,
+        tokenizer=tokenizer,
+        data_collator=data_collator,
+        callbacks=callbacks,
+        **split_dataset(dataset, data_args, training_args)
+    )
+
+    # Training
+    if training_args.do_train:
+        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
+        trainer.save_model()
+        trainer.log_metrics("train", train_result.metrics)
+        trainer.save_metrics("train", train_result.metrics)
+        trainer.save_state()
+        if trainer.is_world_process_zero() and finetuning_args.plot_loss:
+            plot_loss(training_args.output_dir, keys=["loss", "eval_loss"])
+
+    # Evaluation
+    if training_args.do_eval:
+        metrics = trainer.evaluate(metric_key_prefix="eval")
+        try:
+            perplexity = math.exp(metrics["eval_loss"])
+        except OverflowError:
+            perplexity = float("inf")
+
+        metrics["perplexity"] = perplexity
+        trainer.log_metrics("eval", metrics)
+        trainer.save_metrics("eval", metrics)
+
+    # Create model card
+    create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)