Update app.py

app.py

@@ -1,64 +1,132 @@
-import spaces  # Import spaces at the top
+import os
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from threading import Thread
+from typing import Iterator
+
+# Constants
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 1024
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+DESCRIPTION = """\
+# Llama-2 7B Chat
+This Space demonstrates model [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta, a Llama 2 model with 7B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
+🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
+🔨 Looking for an even more powerful model? Check out the [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
+"""
 
-# Import the GPU decorator
-from spaces import GPU
+LICENSE = """
+<p/>
+---
+As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
+this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
+"""
 
-# Set the device to use GPU
-device = "cuda"  # Use CUDA for GPU
+# Set the device
+device = "cuda" if torch.cuda.is_available() else "cpu"
 
-# Initialize model and tokenizer
-peft_model_id = "CMLM/ZhongJing-2-1_8b"
+# Model loading with the replacement setup
 base_model_id = "Qwen/Qwen1.5-1.8B-Chat"
-model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map={"cuda": 0})
-model.load_adapter(peft_model_id)
-tokenizer = AutoTokenizer.from_pretrained(
-    "CMLM/ZhongJing-2-1_8b",
-    padding_side="right",
-    trust_remote_code=True,
-    pad_token=''
-)
+model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map="auto")
+model.load_adapter("CMLM/ZhongJing-2-1_8b")
+tokenizer = AutoTokenizer.from_pretrained("CMLM/ZhongJing-2-1_8b", padding_side="right", trust_remote_code=True, pad_token='')
 
-@GPU(duration=120)  # Decorate with GPU usage and specify the duration
-def get_model_response(question):
-    # Create the prompt without context
-    prompt = f"Question: {question}"
-    messages = [
-        {"role": "system", "content": "You are a helpful TCM medical assistant named 仲景中医大语言模型, created by 医哲未来 of Fudan University."},
-        {"role": "user", "content": prompt}
-    ]
+@spaces.GPU
+def generate(
+    message: str,
+    chat_history: list[tuple[str, str]],
+    system_prompt: str,
+    max_new_tokens: int = 1024,
+    temperature: float = 0.6,
+    top_p: float = 0.9,
+    top_k: int = 50,
+    repetition_penalty: float = 1.2,
+) -> Iterator[str]:
+    conversation = []
+    if system_prompt:
+        conversation.append({"role": "system", "content": system_prompt})
+    for user, assistant in chat_history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": message})
 
-    # Prepare the input
-    text = tokenizer.apply_chat_template(
-        messages,
-        tokenize=False,
-        add_generation_prompt=True
-    )
-    model_inputs = tokenizer([text], return_tensors="pt").to(device)
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
+        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
+        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
+    input_ids = input_ids.to(model.device)
 
-    # Generate the response
+    outputs = []
     generated_ids = model.generate(
-        model_inputs.input_ids,
-        max_new_tokens=512
+        input_ids,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        num_beams=1,
+        repetition_penalty=repetition_penalty
     )
-    generated_ids = [
-        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-    ]
+    outputs.append(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
+    return "".join(outputs)
 
-    # Decode the response
-    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    return response
-
-iface = gr.Interface(
-    fn=get_model_response,  # Directly use the decorated function
-    inputs=["text"],
-    outputs="text",
-    title="仲景GPT-V2-1.8B",
-    description="博极医源，精勤不倦。Unlocking the Wisdom of Traditional Chinese Medicine with AI."
+chat_interface = gr.ChatInterface(
+    fn=generate,
+    additional_inputs=[
+        gr.Textbox(label="System prompt", lines=6),
+        gr.Slider(
+            label="Max new tokens",
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        ),
+        gr.Slider(
+            label="Temperature",
+            minimum=0.1,
+            maximum=4.0,
+            step=0.1,
+            value=0.6,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.9,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=50,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.2,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        ["Hello there! How are you doing?"],
+        ["Can you explain briefly to me what is the Python programming language?"],
+        ["Explain the plot of Cinderella in a sentence."],
+        ["How many hours does it take a man to eat a Helicopter?"],
+        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
+    ],
 )
 
-# Launch the interface with sharing enabled
-iface.launch(share=True)
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
+    chat_interface.render()
+    gr.Markdown(LICENSE)
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()