初始化项目，由ModelHub XC社区提供模型

Model: QuantFactory/Qwen2.5-Coder-7B-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Coder-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text

Qwen2.5-Coder-7B.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3211046f604199a6e655609bc8ce0ac3ebae71203b6d495e74ef001365cb520d
+size 3015940384

Qwen2.5-Coder-7B.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d00178b1111118b5c398174ebf54969631038c33cd95f346d494e59c1373961
+size 4088459552

Qwen2.5-Coder-7B.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06baf05ffb4d63a06c3089694846445e3db5b2176d9bd4c156098343cb1d8cde
+size 3808391456

Qwen2.5-Coder-7B.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d081ec29763e3c676accd4a355b6925bc818ee9dee4cee9c97be9067a8780d
+size 3492368672

Qwen2.5-Coder-7B.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb35b675526337225b8bc3b43cd4ae0ac5b8c3891481c3c28f437027775e422
+size 4431391008

Qwen2.5-Coder-7B.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfb61e0d7e05d04670df919b5073f8e65fa001e46516eac6ead24a64e091d34
+size 4873283872

Qwen2.5-Coder-7B.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06464f568e707c24e1decee3827a0fae01071734f054892a1f3ec071099f1794
+size 4683073824

Qwen2.5-Coder-7B.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aacbe5295fbdcf4cec0386bd3f93b14b63c587c86f93c053750d3f2a29d5980
+size 4457769248

Qwen2.5-Coder-7B.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c63e3d9146bb6ff8e4f735707a3a4b50a70a9d4b05f5f3dec9fae71c40a28b
+size 5315176736

Qwen2.5-Coder-7B.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8202fee422d28033a27776c321f59b1a68855b9528ccba345e0a2d5b6a92e8c3
+size 5757069600

Qwen2.5-Coder-7B.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6fc5e4c07c7cc72d00fc4dce5316df8f1d2bbc5dca83c05f43a670b43b94c1
+size 5444831520

Qwen2.5-Coder-7B.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dd56c8d3a3f03bccc01c15d7e63d81c1ccd37b8e939cb7469b5f72e0ffded7
+size 5315176736

Qwen2.5-Coder-7B.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173bc1db57b45e59aa0a0b9b5d5064f0ae9145d0109b30997de52234d74e1fcc
+size 6254199072

Qwen2.5-Coder-7B.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e09bc605f583ded9b777bfaf2c33c064c2a2e62cec5662db1795fd7f486c3c6
+size 8098525472

README.md

@@ -0,0 +1,110 @@
+
+---
+
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-7B/blob/main/LICENSE
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-7B
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- code
+- qwen
+- qwen-coder
+- codeqwen
+
+---
+
+[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
+
+
+# QuantFactory/Qwen2.5-Coder-7B-GGUF
+This is quantized version of [Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) created using llama.cpp
+
+# Original Model Card
+
+
+# Qwen2.5-Coder-7B
+
+## Introduction
+
+Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). For Qwen2.5-Coder, we release three base language models and instruction-tuned language models, 1.5, 7 and 32 (coming soon) billion parameters. 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. 
+- 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.
+- **Long-context Support** up to 128K tokens.
+
+
+**This repo contains the 7B Qwen2.5-Coder model**, which has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
+- Number of Parameters: 7.61B
+- Number of Paramaters (Non-Embedding): 6.53B
+- Number of Layers: 28
+- Number of Attention Heads (GQA): 28 for Q and 4 for KV
+- Context Length: Full 131,072 tokens
+  - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts.
+  
+**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/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+
+## 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'
+```
+
+### Processing Long Texts
+
+The current `config.json` is set for context length up to 32,768 tokens.
+To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
+
+For supported frameworks, you could add the following to `config.json` to enable YaRN:
+```json
+{
+  ...,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "type": "yarn"
+  }
+}
+```
+
+For deployment, we recommend using vLLM. 
+Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM.
+Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**. 
+We advise adding the `rope_scaling` configuration only when processing long contexts is required.
+
+## Evaluation & Performance
+
+Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-coder/).
+
+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.
+
+```
+@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}
+}
+```

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}