Update README.md
#11
by
haoyang-amd
- opened
README.md
CHANGED
|
@@ -24,7 +24,8 @@ python3 quantize_quark.py \
|
|
| 24 |
--quant_scheme w_fp8_a_fp8 \
|
| 25 |
--kv_cache_dtype fp8 \
|
| 26 |
--num_calib_data 128 \
|
| 27 |
-
--model_export quark_safetensors
|
|
|
|
| 28 |
# If model size is too large for single GPU, please use multi GPU instead.
|
| 29 |
python3 quantize_quark.py \
|
| 30 |
--model_dir $MODEL_DIR \
|
|
@@ -33,6 +34,7 @@ python3 quantize_quark.py \
|
|
| 33 |
--kv_cache_dtype fp8 \
|
| 34 |
--num_calib_data 128 \
|
| 35 |
--model_export quark_safetensors \
|
|
|
|
| 36 |
--multi_gpu
|
| 37 |
```
|
| 38 |
## Deployment
|
|
@@ -53,9 +55,9 @@ The quantization evaluation results are conducted in pseudo-quantization mode, w
|
|
| 53 |
<tr>
|
| 54 |
<td>Perplexity-wikitext2
|
| 55 |
</td>
|
| 56 |
-
<td>
|
| 57 |
</td>
|
| 58 |
-
<td>
|
| 59 |
</td>
|
| 60 |
</tr>
|
| 61 |
</table>
|
|
|
|
| 24 |
--quant_scheme w_fp8_a_fp8 \
|
| 25 |
--kv_cache_dtype fp8 \
|
| 26 |
--num_calib_data 128 \
|
| 27 |
+
--model_export quark_safetensors \
|
| 28 |
+
--no_weight_matrix_merge
|
| 29 |
# If model size is too large for single GPU, please use multi GPU instead.
|
| 30 |
python3 quantize_quark.py \
|
| 31 |
--model_dir $MODEL_DIR \
|
|
|
|
| 34 |
--kv_cache_dtype fp8 \
|
| 35 |
--num_calib_data 128 \
|
| 36 |
--model_export quark_safetensors \
|
| 37 |
+
--no_weight_matrix_merge \
|
| 38 |
--multi_gpu
|
| 39 |
```
|
| 40 |
## Deployment
|
|
|
|
| 55 |
<tr>
|
| 56 |
<td>Perplexity-wikitext2
|
| 57 |
</td>
|
| 58 |
+
<td>3.7797
|
| 59 |
</td>
|
| 60 |
+
<td>3.8561
|
| 61 |
</td>
|
| 62 |
</tr>
|
| 63 |
</table>
|