Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,8 @@ This is a pruned version of the [deepseek-ai/DeepSeek-V3](https://huggingface.co
|
|
19 |
reduced from 256 experts to 160 experts. The pruned model is mainly used for [code](https://huggingface.co/huihui-ai/DeepSeek-V3-Pruned-Coder-411B/blob/main/coding_problems.py) generation.
|
20 |
|
21 |
|
22 |
-
This is a test validation to see if we can prune the model according to professional requirements and still maintain acceptable performance.
|
|
|
23 |
|
24 |
This allows the model to be pruned according to one's needs.
|
25 |
|
|
|
19 |
reduced from 256 experts to 160 experts. The pruned model is mainly used for [code](https://huggingface.co/huihui-ai/DeepSeek-V3-Pruned-Coder-411B/blob/main/coding_problems.py) generation.
|
20 |
|
21 |
|
22 |
+
This is a test validation to see if we can prune the model according to professional requirements and still maintain acceptable performance.
|
23 |
+
The model size has been reduced by about 1/3, and no distortion has occurred.
|
24 |
|
25 |
This allows the model to be pruned according to one's needs.
|
26 |
|