Upload Qwen2MoeForCausalLM

README.md

@@ -1,109 +1,199 @@
-# Upcycled-Qwen1.5-MoE2.7B
-
-This an attemp (probably too naive) to reproduce the upcycling process used to initialize [Qwen1.5-MoE-A2.7B](https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B) using [Qwen1.5-1.8B](Qwen/Qwen1.5-1.8B).
-
-## Upcycling script
-
-```python
-from torch import nn
-from transformers import AutoModelForCausalLM
-from dataclasses import dataclass
-from transformers import AutoModel
-from typing_extensions import Self
-from copy import deepcopy
-
-@dataclass
-class UpcyclingConfig:
-    finegrained_experts: int
-    partitions_from_mlp: int
-
-    @property
-    def upcycling_factor(self) -> int:
-        return self.finegrained_experts // self.partitions_from_mlp
-
-
-def iterate_in_chunks(list1, list2, chunk_size1, chunk_size2):
-    iterations = max(len(list1) // chunk_size1, len(list2) // chunk_size2)
-    for i in range(iterations):
-        start_idx1 = i * chunk_size1
-        end_idx1 = start_idx1 + chunk_size1
-        start_idx2 = i * chunk_size2
-        end_idx2 = start_idx2 + chunk_size2
-        yield (list1[start_idx1:end_idx1], list2[start_idx2:end_idx2])
-
-
-def chunk_linear(linear: nn.Linear, chunks: int, down_proj: bool = False) -> tuple[nn.Linear, ...]:
-    if not down_proj:
-        in_features = linear.in_features
-        out_features = linear.out_features // chunks
-    else:
-        in_features = linear.in_features // chunks
-        out_features = linear.out_features
-
-    weights = linear.weight.chunk(chunks)
-    biases = linear.bias.chunk(chunks) if linear.bias is not None else [None] * chunks
-    linear_layers = []
-    for weight, bias in zip(weights, biases):
-        new_linear = nn.Linear(
-            in_features=in_features, out_features=out_features, bias=bias is not None
-        )
-        new_linear.weight = nn.Parameter(weight.clone())  # Clone weights to ensure they are not shared
-        if bias is not None:
-            new_linear.bias = nn.Parameter(bias.clone())  # Clone bias if it exists
-        linear_layers.append(new_linear)
-    return tuple(linear_layers)
-
-
-class UpcycledModelMixin:
-    sparse_moe_block_cls: type
-
-    @classmethod
-    def upcycled_from(cls, source_model, config: UpcyclingConfig) -> Self:
-        upcycled_model_config = cls.config_class(**source_model.config.to_dict())
-        if hasattr(upcycled_model_config, "shared_expert_intermediate_size"):
-            upcycled_model_config.shared_expert_intermediate_size = source_model.config.intermediate_size
-
-        upcycled_model = cls(upcycled_model_config)
-        upcycled_model.model.embed_tokens = source_model.model.embed_tokens
-
-        for upcycled_layer, layer in zip(upcycled_model.model.layers, source_model.model.layers):
-            upcycled_layer.self_attn = layer.self_attn
-            upcycled_mlp_layers = [deepcopy(layer.mlp) for _ in range(config.upcycling_factor)]
-
-            if hasattr(upcycled_layer.mlp, "shared_expert"):
-                upcycled_layer.mlp.shared_expert = upcycled_mlp_layers.pop(-1)
-
-            for experts, mlp in iterate_in_chunks(upcycled_layer.mlp.experts, upcycled_mlp_layers, 4, 1):
-                gate_projs = chunk_linear(mlp[0].gate_proj, 4, down_proj=False)
-                up_projs = chunk_linear(mlp[0].up_proj, 4, down_proj=False)
-                down_projs = chunk_linear(mlp[0].down_proj, 4, down_proj=True)
-                for i, expert in enumerate(experts):
-                    expert.gate_proj = gate_projs[i]
-                    expert.up_proj = up_projs[i]
-                    expert.down_proj = down_projs[i]
-                    expert.act_fn = deepcopy(mlp[0].act_fn)
-
-            upcycled_layer.input_layernorm = layer.input_layernorm
-            upcycled_layer.post_attention_layernorm = layer.post_attention_layernorm
-
-        upcycled_model.lm_head = source_model.lm_head
-        return upcycled_model
-
-
-from transformers import Qwen2MoeForCausalLM as _Qwen2MoeForCausalLM
-from transformers.models.qwen2.modeling_qwen2 import Qwen2MLP
-from transformers.models.qwen2_moe.modeling_qwen2_moe import Qwen2MoeSparseMoeBlock
-
-class Qwen2MoeForCausalLM(UpcycledModelMixin, _Qwen2MoeForCausalLM):
-    sparse_moe_block_cls = Qwen2MoeSparseMoeBlock
-
-
-source_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-1.8B")
-model = Qwen2MoeForCausalLM.upcycled_from(
-    source_model,
-    UpcyclingConfig(
-        finegrained_experts=64,
-        partitions_from_mlp=4,
-    ),
-)
-```
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 1408,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts": 60,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 5504,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa08aff3e4dd7f4cb7c97a995bf20b945151e67caaec1ffa21fcad963aaa3238
+size 4998348448

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60629f8099a4c2ced043ce3486ffdbd9b2fc05b1d21b6038480a8ea012ee61e
+size 4993666912

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d627b48b981e327555ea52ddd7f9f6fef09ef37663a2a0fc1e127a9623207eb
+size 4993682688

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed0aaa105d9b4cfeb5211b81ee683797ba45683c0850a23206b20645b70240e
+size 4993666896

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7257218ff3dbb12354489ed83e67de74fe619c15a44e9e57e4cf32e9e131e33
+size 4993667040

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133b38b85c3c71a3973672ed65fb6081ee573c16b815d238e96ef3f6d348e976
+size 4993667352

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc2aae38b11b0908340821b73ba5912052ac8f764db648b02f8901c5b3faa28
+size 4993683128

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c5550838172649d89c8fc6548878997b269146ded7ff7674523adab07be815
+size 4993667320

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73be2628ff33a392edadc788d2abf0e7efebb1e640d9a22e01b8ebf14dea0ea
+size 4993667336

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959fcfbd31660a38ed5f90234def80e6d22929516ffd442faa5f63efe074dcd1
+size 4993667352

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:defe36cc3621d7f982a32aa23899937d007220bdc8db87fd06ead4760a036c41
+size 4869703976

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6e8547b8884ccba68b2f4a275e6a2b08bb94d8f25c9235b02617d2d6842ac3
+size 1244659840