Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,7 @@ Below is an example of how to quantize this model:
|
|
| 34 |
|
| 35 |
```bash
|
| 36 |
cd Quark/examples/torch/language_modeling/llm_ptq/
|
| 37 |
-
exclude_layers="lm_head *self_attn* *mlp.gate *eh_proj"
|
| 38 |
python3 quantize_quark.py --model_dir $MODEL_DIR \
|
| 39 |
--quant_scheme w_mxfp4_a_mxfp4 \
|
| 40 |
--num_calib_data 32 \
|
|
|
|
| 34 |
|
| 35 |
```bash
|
| 36 |
cd Quark/examples/torch/language_modeling/llm_ptq/
|
| 37 |
+
exclude_layers="lm_head *self_attn* *mlp.gate *eh_proj *shared_head.head"
|
| 38 |
python3 quantize_quark.py --model_dir $MODEL_DIR \
|
| 39 |
--quant_scheme w_mxfp4_a_mxfp4 \
|
| 40 |
--num_calib_data 32 \
|