amd
/

DeepSeek-R1-MXFP4-Preview

8-bit precision

Model card Files Files and versions

linzhao-amd commited on Aug 4

Commit

855b652

·

verified ·

1 Parent(s): 5751a6a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ You can either perform the dequantization manually using this [conversion script
 **Quantization scripts:**
 ```
 cd Quark/examples/torch/language_modeling/llm_ptq/
-python3 quantize_quark.py --model_dir deepseek-ai/DeepSeek-R1 \
                           --quant_scheme w_mxfp4_a_mxfp4 \
                           --group_size 32 \
                           --num_calib_data 128 \

 **Quantization scripts:**
 ```
 cd Quark/examples/torch/language_modeling/llm_ptq/
+python3 quantize_quark.py --model_dir $MODEL_DIR \
                           --quant_scheme w_mxfp4_a_mxfp4 \
                           --group_size 32 \
                           --num_calib_data 128 \