codefuse-admin commited on
Commit
6565431
1 Parent(s): 74557cd

update readme.md to add links to github repos

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -17,6 +17,17 @@ tasks:
17
  CodeFuse-13B is a 13 billion parameter code generation model trained on the GPT-NeoX framework, capable of handling code sequences of up to 4096 characters. This model was pretrained on a dataset consisting of 1000B token code, Chinese, and English data, covering over 40 programming languages. To further enhance the effectiveness and quality of the generated code, the model was fine-tuned on the CodeFuse-Evol-instruction-66k dataset, enabling it to produce more accurate, efficient, and compliant code. Pass@1 achieved 37.1% on the HumanEval evaluation set(BeamSearch strategy, BeamSize=3).
18
 
19
 
 
 
 
 
 
 
 
 
 
 
 
20
  ## Requirements
21
  * Python 3.8 or above.
22
  * PyTorch 1.12 or above, with a recommendation for 2.0 or above.
@@ -57,6 +68,16 @@ We notice that the file may be corrupted during transfer process. Please check M
57
  CodeFuse-13B是基于GPT-NeoX框架训练的13B参数代码生成模型,能够处理4096个字符的代码序列。该模型在1000B Token的代码、中文、英文数据数据集上进行预训练,覆盖超过40种编程语言。为了进一步提升生成代码的效果和质量,该模型还在CodeFuse-Evol-instruction-66k数据集上进行了微调,使得该模型能够生成更加准确、高效、符合要求的代码。在HumanEval评测集上Pass@1达到37.1%(采用BeamSearch解码,其中BeamSize=3)。
58
 
59
 
 
 
 
 
 
 
 
 
 
 
60
  ## 要求
61
  * python 3.8及以上版本
62
  * pytorch 1.12及以上版本,推荐2.0及以上版本
 
17
  CodeFuse-13B is a 13 billion parameter code generation model trained on the GPT-NeoX framework, capable of handling code sequences of up to 4096 characters. This model was pretrained on a dataset consisting of 1000B token code, Chinese, and English data, covering over 40 programming languages. To further enhance the effectiveness and quality of the generated code, the model was fine-tuned on the CodeFuse-Evol-instruction-66k dataset, enabling it to produce more accurate, efficient, and compliant code. Pass@1 achieved 37.1% on the HumanEval evaluation set(BeamSearch strategy, BeamSize=3).
18
 
19
 
20
+ ## Code Community
21
+
22
+ **Homepage**: 🏡 https://github.com/codefuse-ai (**Please give us your support with a Star🌟 + Fork🚀 + Watch👀**)
23
+
24
+ + If you wish to fine-tune the model yourself, you can visit ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
25
+
26
+ + If you wish to deploy the model yourself, you can visit ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
27
+
28
+ + If you wish to see a demo of the model, you can visit ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨
29
+
30
+
31
  ## Requirements
32
  * Python 3.8 or above.
33
  * PyTorch 1.12 or above, with a recommendation for 2.0 or above.
 
68
  CodeFuse-13B是基于GPT-NeoX框架训练的13B参数代码生成模型,能够处理4096个字符的代码序列。该模型在1000B Token的代码、中文、英文数据数据集上进行预训练,覆盖超过40种编程语言。为了进一步提升生成代码的效果和质量,该模型还在CodeFuse-Evol-instruction-66k数据集上进行了微调,使得该模型能够生成更加准确、高效、符合要求的代码。在HumanEval评测集上Pass@1达到37.1%(采用BeamSearch解码,其中BeamSize=3)。
69
 
70
 
71
+ ## 代码社区
72
+ **大本营**: 🏡 https://github.com/codefuse-ai (**欢迎为我们的项目一键三连 Star🌟 + Fork🚀 + Watch👀**)
73
+
74
+ + 如果您想自己微调该模型,可以访问 ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
75
+
76
+ + 如果您想自己部署该模型,可以访问 ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
77
+
78
+ + 如果您想观看该模型示例,可以访问 ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨
79
+
80
+
81
  ## 要求
82
  * python 3.8及以上版本
83
  * pytorch 1.12及以上版本,推荐2.0及以上版本