初始化项目，由ModelHub XC社区提供模型

Model: CaptainHPY/Qwen2.5-7B-R1-GGUF Source: Original Platform
2026-09-20 06:16:16 +08:00
commit 8cac60cad0
7 changed files with 230 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,39 @@
+*.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
+Qwen2.5-7B-R1-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-R1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-R1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-R1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Qwen2.5-7B-R1-F16.gguf
+++ b/Qwen2.5-7B-R1-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093831394fe5a14ddf5e5a8673f72f2cd6f853369eab0e1b55f5b9c99ce3f8b1
+size 15237851328
--- a/Qwen2.5-7B-R1-Q4_K_M.gguf
+++ b/Qwen2.5-7B-R1-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d683419b6bd8fdd82939a1e0089b5d51e77eb3a549203d23438d487fc7d7de63
+size 4683071680
--- a/Qwen2.5-7B-R1-Q5_K_M.gguf
+++ b/Qwen2.5-7B-R1-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9e18662c2f4c5d5f74e13fef69f70320c62fc321e44f00327a0f0c735ea3e5
+size 5444829376
--- a/Qwen2.5-7B-R1-Q8_0.gguf
+++ b/Qwen2.5-7B-R1-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0d2a98d9fc25ee6fdb20801844dc34a8a1f0172a525966d418d2e9a9bd56a2
+size 8098523328
--- a/README.md
+++ b/README.md
@@ -0,0 +1,119 @@
+---
+license: apache-2.0
+datasets:
+  - unsloth/OpenMathReasoning-mini
+  - open-r1/DAPO-Math-17k-Processed
+base_model:
+  - unsloth/Qwen2.5-7B-Instruct-bnb-4bit
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+  - transformers
+  - unsloth
+  - trl
+---
+
+**GGUFs of [CaptainHPY/Qwen2.5-7B-R1](https://huggingface.co/CaptainHPY/Qwen2.5-7B-R1).**
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/captainhpy-beijing-university-of-technology/tiny-reasoning/runs/6zmbkin8) 
+
+## Quickstart
+
+**Ollama:**
+
+1. Install ollama:
+
+```bash
+apt-get update
+apt-get install pciutils -y
+curl -fsSL https://ollama.com/install.sh | sh
+```
+
+2. Run the model:
+
+```bash
+ollama run hf.co/CaptainHPY/Qwen2.5-7B-R1-GGUF:Q4_K_M
+```
+
+**Llama.cpp:**
+
+1. Install llama.cpp:
+
+```bash
+apt-get update
+apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
+git clone https://github.com/ggml-org/llama.cpp
+cmake llama.cpp -B llama.cpp/build \
+    -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON
+cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-gguf-split
+cp llama.cpp/build/bin/llama-* llama.cpp
+```
+
+2. Pull from HuggingFace:
+
+```bash
+./llama.cpp/llama-cli \
+    -hf CaptainHPY/Qwen2.5-7B-R1-GGUF:Q4_K_M \
+    --jinja -ngl 99 --threads -1 --ctx-size 32684 \
+    --temp 0.7 --min-p 0.0 --top-p 0.80 --top-k 20 --repeat-penalty 1.05
+```
+
+3. Or Download the model after `pip install huggingface_hub hf_transfer`:
+
+```python
+import os
+os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
+from huggingface_hub import snapshot_download
+snapshot_download(
+    repo_id = "CaptainHPY/Qwen2.5-7B-R1-GGUF",
+    local_dir = "CaptainHPY/Qwen2.5-7B-R1-GGUF",
+    allow_patterns = ["*Q4_K_M*"],
+)
+```
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```
+
+Cite Qwen2.5 as:
+
+```bibtex
+@misc{qwen2.5,
+    title = {Qwen2.5: A Party of Foundation Models},
+    url = {https://qwenlm.github.io/blog/qwen2.5/},
+    author = {Qwen Team},
+    month = {September},
+    year = {2024}
+}
+@article{qwen2,
+      title={Qwen2 Technical Report}, 
+      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
+      journal={arXiv preprint arXiv:2407.10671},
+      year={2024}
+}
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.7.5",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}