leafspark commited on
Commit
5a5087b
·
verified ·
1 Parent(s): 2e89d8d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -6
README.md CHANGED
@@ -9,6 +9,10 @@ tags:
9
  - gguf
10
  - f32
11
  - f16
 
 
 
 
12
  - humaneval
13
  license: mit
14
  ---
@@ -17,14 +21,16 @@ license: mit
17
 
18
  WaveCoder 🌊 is a series of large language models (LLMs) for the coding domain.
19
 
20
- Apologies for the incomplete model details, the GitHub repo doesn't exist and I'm currently trying to quant all the models.
21
-
22
  ## Model Details
23
 
24
  ### Model Description
25
 
26
  WaveCoder 🌊 is a series of large language models (LLMs) for the coding domain, designed to solve relevant problems in the field of code through instruction-following learning. Its training dataset was generated from a subset of code-search-net data using a generator-discriminator framework based on LLMs that we proposed, covering four general code-related tasks: code generation, code summary, code translation, and code repair.
27
 
 
 
 
 
28
  - **Developed by:** Yu, Zhaojian and Zhang, Xin and Shang, Ning and Huang, Yangyu and Xu, Can and Zhao, Yishujie and Hu, Wenxiang and Yin, Qiufeng
29
  - **Model type:** Large Language Model
30
  - **Language(s) (NLP):** English
@@ -32,12 +38,12 @@ WaveCoder 🌊 is a series of large language models (LLMs) for the coding domain
32
 
33
  ### Model Sources
34
 
35
- - **Repository:** [More Information Needed]
36
- - **Paper [optional]:** [More Information Needed]
37
- - **Demo [optional]:** [More Information Needed]
38
 
39
  ## Uses
40
 
41
- Coding
42
 
43
  ## Original: [https://huggingface.co/microsoft/wavecoder-ds-6.7b](https://huggingface.co/microsoft/wavecoder-ds-6.7b)
 
9
  - gguf
10
  - f32
11
  - f16
12
+ - q2
13
+ - q8
14
+ - q6
15
+ - q4_k_m
16
  - humaneval
17
  license: mit
18
  ---
 
21
 
22
  WaveCoder 🌊 is a series of large language models (LLMs) for the coding domain.
23
 
 
 
24
  ## Model Details
25
 
26
  ### Model Description
27
 
28
  WaveCoder 🌊 is a series of large language models (LLMs) for the coding domain, designed to solve relevant problems in the field of code through instruction-following learning. Its training dataset was generated from a subset of code-search-net data using a generator-discriminator framework based on LLMs that we proposed, covering four general code-related tasks: code generation, code summary, code translation, and code repair.
29
 
30
+ WaveCoder-ds = Trained using CodeOcean dataset
31
+ WaveCoder-pro = Trained using GPT-4 synthetic data
32
+ WaveCoder-ultra = Trained using enhanced GPT-4 synthetic data
33
+
34
  - **Developed by:** Yu, Zhaojian and Zhang, Xin and Shang, Ning and Huang, Yangyu and Xu, Can and Zhao, Yishujie and Hu, Wenxiang and Yin, Qiufeng
35
  - **Model type:** Large Language Model
36
  - **Language(s) (NLP):** English
 
38
 
39
  ### Model Sources
40
 
41
+ - **Repository:** [https://huggingface.co/microsoft/wavecoder-ds-6.7b](https://huggingface.co/microsoft/wavecoder-ds-6.7b)
42
+ - **Paper :** [More Information Needed]
43
+ - **Demo :** [More Information Needed]
44
 
45
  ## Uses
46
 
47
+ Coding/Refactoring/Cleanup/Fixing Code
48
 
49
  ## Original: [https://huggingface.co/microsoft/wavecoder-ds-6.7b](https://huggingface.co/microsoft/wavecoder-ds-6.7b)