Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,9 @@ This project has received some objections, and we shouldn't force everyone to li
|
|
| 25 |
|
| 26 |
# Note
|
| 27 |
|
| 28 |
-
We will refer to [huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned](https://huggingface.co/huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned) for a pruning test of [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3), and it
|
|
|
|
|
|
|
| 29 |
|
| 30 |
# About
|
| 31 |
|
|
|
|
| 25 |
|
| 26 |
# Note
|
| 27 |
|
| 28 |
+
We will refer to [huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned](https://huggingface.co/huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned) for a pruning test of [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3), and it
|
| 29 |
+
|
| 30 |
+
**DeepSeek-V3-Pruned-Coder-411B** is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation. It will be released soon..
|
| 31 |
|
| 32 |
# About
|
| 33 |
|