commit b261b13e16b194b3f4502ca0fd365dfda55d2535 Author: ModelHub XC Date: Mon Sep 21 04:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Volko76/Qwen2.5-Coder-0.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2ba43b7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.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-coder-0.5b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-0.5b.bf16.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-0.5b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-0.5b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-0.5b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-0.5b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-0.5b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1bf247d --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B/blob/main/LICENSE +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +base_model: +- Qwen/Qwen2.5-0.5B +pipeline_tag: text-generation +library_name: transformers +tags: +- code +- qwen +- qwen-coder +- codeqwen +- autoquant +- gguf +--- + +# Qwen2.5-Coder-0.5B + +## Introduction + +Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: + +- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o. +- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. + +**This repo contains the 0.5B Qwen2.5-Coder model**, which has the following features: +- Type: Causal Language Models +- Training Stage: Pretraining +- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings +- Number of Parameters: 0.49B +- Number of Paramaters (Non-Embedding): 0.36B +- Number of Layers: 24 +- Number of Attention Heads (GQA): 14 for Q and 2 for KV +- Context Length: Full 32,768 tokens + +**We do not recommend using base language models for conversations.** Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., or fill in the middle tasks on this model. + +For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), [Documentation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs/2409.12186). + +## Requirements + +The code of Qwen2.5-Coder has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. + +With `transformers<4.37.0`, you will encounter the following error: +``` +KeyError: 'qwen2' +``` + + +## Evaluation & Performance + +Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/). + +For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). + +## Citation + +If you find our work helpful, feel free to give us a cite. + +``` +@article{hui2024qwen2, + title={Qwen2. 5-Coder Technical Report}, + author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others}, + journal={arXiv preprint arXiv:2409.12186}, + 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} +} +``` \ No newline at end of file diff --git a/qwen2.5-coder-0.5b.Q2_K.gguf b/qwen2.5-coder-0.5b.Q2_K.gguf new file mode 100644 index 0000000..84b4706 --- /dev/null +++ b/qwen2.5-coder-0.5b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd07227d2b253e309de1192cd31fe3d08c151db6397aca5464bdf774b29d5201 +size 338607328 diff --git a/qwen2.5-coder-0.5b.Q3_K_M.gguf b/qwen2.5-coder-0.5b.Q3_K_M.gguf new file mode 100644 index 0000000..c565547 --- /dev/null +++ b/qwen2.5-coder-0.5b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee1559a7e80bdae234d360dcc127df359e845fa084faa41b4cf6d223d8e2662 +size 355466464 diff --git a/qwen2.5-coder-0.5b.Q4_K_M.gguf b/qwen2.5-coder-0.5b.Q4_K_M.gguf new file mode 100644 index 0000000..5074015 --- /dev/null +++ b/qwen2.5-coder-0.5b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f61f010bfeed1a7b36e3c0758c9ebf4110a7f966426fe0954a30b8e3827481 +size 397807840 diff --git a/qwen2.5-coder-0.5b.Q5_K_M.gguf b/qwen2.5-coder-0.5b.Q5_K_M.gguf new file mode 100644 index 0000000..6a63860 --- /dev/null +++ b/qwen2.5-coder-0.5b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d695d1d3a7a5fd8cb3f565fb7ed37753ed162d695f77b8ac069e4e9356894d +size 420085984 diff --git a/qwen2.5-coder-0.5b.Q6_K.gguf b/qwen2.5-coder-0.5b.Q6_K.gguf new file mode 100644 index 0000000..f1593d0 --- /dev/null +++ b/qwen2.5-coder-0.5b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061b02146edb986ce29e357d31094f4c0d9333d8ae6abc87408f28d4851694da +size 505736416 diff --git a/qwen2.5-coder-0.5b.Q8_0.gguf b/qwen2.5-coder-0.5b.Q8_0.gguf new file mode 100644 index 0000000..1fac3ae --- /dev/null +++ b/qwen2.5-coder-0.5b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a563b0822d92aa051118fe9e2a1bea30802ead74e464980cbeac058041daed6a +size 531068128 diff --git a/qwen2.5-coder-0.5b.bf16.gguf b/qwen2.5-coder-0.5b.bf16.gguf new file mode 100644 index 0000000..16f4f49 --- /dev/null +++ b/qwen2.5-coder-0.5b.bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5121dc6d7f75962f441101cdb56ea33047e6880d4dbffd52f198b72198e7d7 +size 994156768