JustinLin610 commited on
Commit
ed82d97
1 Parent(s): 25fdff3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -1
README.md CHANGED
@@ -1,5 +1,59 @@
1
  ---
2
  license: other
3
  license_name: tongyi-qianwen
4
- license_link: LICENSE
 
 
 
 
 
5
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: other
3
  license_name: tongyi-qianwen
4
+ license_link: https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat-GGUF/blob/main/LICENSE
5
+ language:
6
+ - en
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - chat
10
  ---
11
+
12
+ # CodeQwen1.5-7B-Chat-GGUF
13
+
14
+
15
+ ## Introduction
16
+
17
+ CodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes.
18
+
19
+ * Strong code generation capabilities and competitve performance across a series of benchmarks;
20
+ * Supporting long context understanding and generation with the context length of 64K tokens;
21
+ * Supporting 92 coding languages
22
+ * Excellent performance on text-to-SQL, bug fix, etc.
23
+
24
+
25
+ For more details, please refer to our [blog post](https://qwenlm.github.io/blog/codeqwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
26
+ In this repo, we provide quantized models in the GGUF formats, including `q2_k`, `q3_k_m`, `q4_0`, `q4_k_m`, `q5_0`, `q5_k_m`, `q6_k` and `q8_0`.
27
+
28
+
29
+ ## Model Details
30
+ CodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.
31
+
32
+ ## Requirements
33
+ We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and install it following the official guide.
34
+
35
+
36
+ ## How to use
37
+ Cloning the repo may be inefficient, and thus you can manually download the GGUF file that you need or use `huggingface-cli` (`pip install huggingface_hub`) as shown below:
38
+ ```shell
39
+ huggingface-cli download Qwen/CodeQwen1.5-7B-Chat-GGUF codeqwen1_5-7b-chat-q5_k_m.gguf --local-dir . --local-dir-use-symlinks False
40
+ ```
41
+
42
+ We demonstrate how to use `llama.cpp` to run Qwen1.5:
43
+ ```shell
44
+ ./main -m codeqwen1_5-7b-chat-q5_k_m.gguf -n 512 --color -i -cml -f prompts/chat-with-qwen.txt
45
+ ```
46
+
47
+
48
+ ## Citation
49
+
50
+ If you find our work helpful, feel free to give us a cite.
51
+
52
+ ```
53
+ @article{qwen,
54
+ title={Qwen Technical Report},
55
+ author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
56
+ journal={arXiv preprint arXiv:2309.16609},
57
+ year={2023}
58
+ }
59
+ ```