初始化项目，由ModelHub XC社区提供模型

Model: cmcheng/DeepMath-GRPO_Qwen2.5-0.5B-Instruct Source: Original Platform
2026-09-21 19:08:22 +08:00
commit bc7334ea26
10 changed files with 369 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/.ipynb_checkpoints/README-checkpoint.md
+++ b/.ipynb_checkpoints/README-checkpoint.md
@@ -0,0 +1,84 @@
+---
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+library_name: transformers
+model_name: DeepMath-GRPO_Qwen2.5-0.5B-Instruct
+tags:
+- generated_from_trainer
+- grpo
+- trl
+licence: license
+---
+
+# GRPO 微调 Qwen2.5-0.5B-Instruct
+- 训练环境：
+    - 显卡：2 * NVIDIA 4080 32GB
+    - 加速框架：DeepSpeed，采用 bf16 混合精度训练
+
+- 训练集：zwhe99/DeepMath-103K
+- 训练数据量：97870
+- 测试数据量：5152
+- 验证集选取：从测试集随机抽取 100 条
+- 最大迭代步数限制： 5000
+- 训练参数：
+```python
+grpo_config = GRPOConfig(
+        # ---- 基础配置 ----
+        output_dir="./deepmath_grpo_output",
+        save_strategy='best',
+        save_total_limit=5,
+        #save_steps=100,   
+        # ---- 批次大小 ----
+        per_device_train_batch_size=4,          # 每设备批次大小
+        per_device_eval_batch_size=4,
+        gradient_accumulation_steps=4,           # 梯度累积步数
+        # 有效批次大小 = 4 * 2 * 8 GPUs = 64（与论文 512 有差距，可根据硬件调整）
+        
+        # ---- 训练步数 ----
+        max_steps=1000,                          # 论文中 DeepMath-Zero 训练 500 步
+        #num_train_epochs=1,
+        # ---- 推理框架配置
+        use_vllm=True,
+        vllm_gpu_memory_utilization=0.3,
+
+        # 评估策略
+        eval_strategy='steps',
+        eval_steps=50,
+        metric_for_best_model="eval_reward",
+        greater_is_better=True,
+        logging_strategy='epoch',
+        logging_dir="train_logs/",
+        load_best_model_at_end=True,
+
+        # ---- 学习率 ----
+        learning_rate=1e-6,                     # 论文 Table 5: lr=1e-6
+        
+        # ---- GRPO 特有参数 ----
+        num_generations=settings.GROUP_SIZE_TRAIN,  # 4                    
+        num_generations_eval=settings.GROUP_SIZE_EVAL,  # 4
+        generation_batch_size=4,                # 生成批次大小
+        max_completion_length=2048,             # 最大生成长度（论文推理时为 32768，训练时 2048）
+        loss_type='grpo', # 使用标准 GRPO 算法训练
+        
+        # ---- KL 散度控制 ----
+        beta=0.001,                          # 论文 Table 5: kl_coef=1e-3
+        
+        # ---- 裁剪参数 ----
+        epsilon=0.2,                     # 论文 Table 5: clip_ratio_low=0.2
+        epsilon_high=0.28,                   # 论文 Table 5: clip_ratio_high=0.28
+        
+        # ---- 温度参数 ----
+        temperature=1.0,                        # 论文 Table 5: temperature=1.0 (Zero RL)
+    
+        # ---- 内存优化 ----
+        bf16=torch.cuda.is_bf16_supported(),
+        fp16=not torch.cuda.is_bf16_supported(),
+        gradient_checkpointing=True,
+        
+        # ---- 报告与日志 ----
+        report_to="tensorboard",                       # 可改为 "wandb" 启用 wandb 日志
+        run_name="deepmath-grpo-qwen-0.5b-instruct",
+
+        # 随机种子
+        seed=settings.SEED
+    )
+```
--- a/README.md
+++ b/README.md
@@ -0,0 +1,84 @@
+---
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+library_name: transformers
+model_name: DeepMath-GRPO_Qwen2.5-0.5B-Instruct
+tags:
+- generated_from_trainer
+- grpo
+- trl
+licence: license
+---
+
+# GRPO 微调 Qwen2.5-0.5B-Instruct
+- 训练环境：
+    - 显卡：2 * NVIDIA 4080 32GB
+    - 加速框架：DeepSpeed，采用 bf16 混合精度训练
+
+- 训练集：[zwhe99/DeepMath-103K](https://huggingface.co/datasets/zwhe99/DeepMath-103K)
+- 训练数据量：97870
+- 测试数据量：5152
+- 验证集选取：从测试集随机抽取 100 条
+- 最大迭代步数限制： 5000
+- 训练参数：
+```python
+grpo_config = GRPOConfig(
+        # ---- 基础配置 ----
+        output_dir="./deepmath_grpo_output",
+        save_strategy='best',
+        save_total_limit=5,
+        #save_steps=100,   
+        # ---- 批次大小 ----
+        per_device_train_batch_size=4,          # 每设备批次大小
+        per_device_eval_batch_size=4,
+        gradient_accumulation_steps=4,           # 梯度累积步数
+        # 有效批次大小 = 4 * 2 * 8 GPUs = 64（与论文 512 有差距，可根据硬件调整）
+        
+        # ---- 训练步数 ----
+        max_steps=1000,                          # 论文中 DeepMath-Zero 训练 500 步
+        #num_train_epochs=1,
+        # ---- 推理框架配置
+        use_vllm=True,
+        vllm_gpu_memory_utilization=0.3,
+
+        # 评估策略
+        eval_strategy='steps',
+        eval_steps=50,
+        metric_for_best_model="eval_reward",
+        greater_is_better=True,
+        logging_strategy='epoch',
+        logging_dir="train_logs/",
+        load_best_model_at_end=True,
+
+        # ---- 学习率 ----
+        learning_rate=1e-6,                     # 论文 Table 5: lr=1e-6
+        
+        # ---- GRPO 特有参数 ----
+        num_generations=settings.GROUP_SIZE_TRAIN,  # 4                    
+        num_generations_eval=settings.GROUP_SIZE_EVAL,  # 4
+        generation_batch_size=4,                # 生成批次大小
+        max_completion_length=2048,             # 最大生成长度（论文推理时为 32768，训练时 2048）
+        loss_type='grpo', # 使用标准 GRPO 算法训练
+        
+        # ---- KL 散度控制 ----
+        beta=0.001,                          # 论文 Table 5: kl_coef=1e-3
+        
+        # ---- 裁剪参数 ----
+        epsilon=0.2,                     # 论文 Table 5: clip_ratio_low=0.2
+        epsilon_high=0.28,                   # 论文 Table 5: clip_ratio_high=0.28
+        
+        # ---- 温度参数 ----
+        temperature=1.0,                        # 论文 Table 5: temperature=1.0 (Zero RL)
+    
+        # ---- 内存优化 ----
+        bf16=torch.cuda.is_bf16_supported(),
+        fp16=not torch.cuda.is_bf16_supported(),
+        gradient_checkpointing=True,
+        
+        # ---- 报告与日志 ----
+        report_to="tensorboard",                       # 可改为 "wandb" 启用 wandb 日志
+        run_name="deepmath-grpo-qwen-0.5b-instruct",
+
+        # 随机种子
+        seed=settings.SEED
+    )
+```
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.15.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.15.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ef3d400b8894345a36a84c6239fb8287c7997797b9af25e21d0b9b6a2930c1
+size 1260367448
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e81fcdb17315fb8ff9984439b3d06535a0fee939d871b801a74025ca81bb36
+size 9169