amd
/

DeepSeek-R1-0528-BF16

Text Generation

text-generation-inference

Model card Files Files and versions

kewang2 commited on Nov 14, 2025

Commit

1d97c92

·

verified ·

1 Parent(s): 60834d9

Update README.md

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -28,8 +28,6 @@ This model is adapted from `unsloth/DeepSeek-R1-0528-BF16` by adding an MTP laye
 - 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.
 - Therefore, when quantizing with AMD-Quark, you **must add the `--skip_evaluation` option** to skip the evaluation step and only perform quantization.
-For further details or issues, please refer to the [AMD-Quark](https://quark.docs.amd.com/latest/index.html) documentation or contact the respective developers.
 Below is an example of how to quantize this model:
 ```bash

 - 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.
 - Therefore, when quantizing with AMD-Quark, you **must add the `--skip_evaluation` option** to skip the evaluation step and only perform quantization.
 Below is an example of how to quantize this model:
 ```bash