bowenbaoamd commited on
Commit
159dc7b
·
verified ·
1 Parent(s): 498ec02

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -29,6 +29,7 @@ To enable MTP layer loading and quantization, this model is adapted from `unslot
29
  - When loading this model, you must set `trust_remote_code=True` to ensure that changes related to the MTP layer in `modeling_deepseek.py` take effect.
30
  - After loading this model with `transformers`, **evaluation should NOT be performed directly**. The reason is that the forward function for the added MTP layer in `modeling_deepseek.py` is implemented only for calibration during the quantization process, so computation is not guaranteed to be the same as the original DeepSeek-R1-0528.
31
  - Therefore, when quantizing with AMD-Quark, you **must add the `--skip_evaluation` option** to skip the evaluation step and only perform quantization.
 
32
 
33
  Below is an example of how to quantize this model:
34
 
 
29
  - When loading this model, you must set `trust_remote_code=True` to ensure that changes related to the MTP layer in `modeling_deepseek.py` take effect.
30
  - After loading this model with `transformers`, **evaluation should NOT be performed directly**. The reason is that the forward function for the added MTP layer in `modeling_deepseek.py` is implemented only for calibration during the quantization process, so computation is not guaranteed to be the same as the original DeepSeek-R1-0528.
31
  - Therefore, when quantizing with AMD-Quark, you **must add the `--skip_evaluation` option** to skip the evaluation step and only perform quantization.
32
+ - To skip quantization for the MTP layers, set `exclude_layers="lm_head *self_attn* *mlp.gate *eh_proj *shared_head.head model.layers.61.*"`.
33
 
34
  Below is an example of how to quantize this model:
35