Hugging Face's logo

huihui-ai
/
Moonlight-16B-A3B-Instruct-abliterated-Pruned

Text Generation
Transformers
Safetensors
deepseek_v3
abliterated
uncensored
Pruned
conversational
custom_code
Model card Files Community
huihui-ai commited on
Commit
9fb7788
·
verified ·
1 Parent(s): 7150ad7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -11,7 +11,8 @@ tags:
11
  # huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned
12
 
13
 
14
- This is a pruned version of the [huihui-ai/Moonlight-16B-A3B-Instruct-abliterated](https://huggingface.co/huihui-ai/Moonlight-16B-A3B-Instruct-abliterated), reduced from 64 experts to 32 experts. The pruned system is mainly used for code generation.
 
15
 
16
 
17
  This is a test validation to see if we can prune the model according to professional requirements and still maintain acceptable performance. The model size has been reduced by about half, and no distortion has occurred.
 
11
  # huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned
12
 
13
 
14
+ This is a pruned version of the [huihui-ai/Moonlight-16B-A3B-Instruct-abliterated](https://huggingface.co/huihui-ai/Moonlight-16B-A3B-Instruct-abliterated),
15
+ reduced from 64 experts to 32 experts. The pruned system is mainly used for [code](https://huggingface.co/huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned/blob/main/coding_problems.py) generation.
16
 
17
 
18
  This is a test validation to see if we can prune the model according to professional requirements and still maintain acceptable performance. The model size has been reduced by about half, and no distortion has occurred.