Update README.md

README.md

@@ -68,7 +68,7 @@ This model was created with [llm-compressor](https://github.com/vllm-project/llm
 
 
 ```bash
-python quantize.py --model_path ibm-granite/granite-3.1-8b-instruct --quant_path "output_dir/granite-3.1-8b-instruct-quantized.w4a16" --calib_size 1024 --dampening_frac 0.01 --observer mse  --actorder dynamic
+python quantize.py --model_path ibm-granite/granite-3.1-8b-instruct --quant_path "output_dir/granite-3.1-8b-instruct-quantized.w4a16" --calib_size 1024 --dampening_frac 0.1 --observer mse  --actorder static
 ```
 
 
@@ -192,18 +192,18 @@ evalplus.evaluate \
 
 | Metric                                  | ibm-granite/granite-3.1-8b-instruct             | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16 |
 |-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
-| ARC-Challenge (Acc-Norm, 25-shot)       | 66.81                             | 66.98                                      |
-| GSM8K (Strict-Match, 5-shot)            | 64.52                             | 68.08                                       |
-| HellaSwag (Acc-Norm, 10-shot)           | 84.18                             | 83.30                                       |
-| MMLU (Acc, 5-shot)                      | 65.52                             | 63.96                                       |
-| TruthfulQA (MC2, 0-shot)                | 60.57                             | 60.62                                        |
-| Winogrande (Acc, 5-shot)                | 80.19                             | 78.61                                        |
-| **Average Score**                       | **70.30**                         | **70.26**                                   |
-| **Recovery**                            | **100.00**                        | **99.94**                                   |
+| ARC-Challenge (Acc-Norm, 25-shot)       | 66.81                             | 66.81                                      |
+| GSM8K (Strict-Match, 5-shot)            | 64.52                             | 65.66                                       |
+| HellaSwag (Acc-Norm, 10-shot)           | 84.18                             | 83.62                                       |
+| MMLU (Acc, 5-shot)                      | 65.52                             | 64.25                                       |
+| TruthfulQA (MC2, 0-shot)                | 60.57                             | 60.17                                        |
+| Winogrande (Acc, 5-shot)                | 80.19                             | 78.37                                        |
+| **Average Score**                       | **70.30**                         | **69.81**                                   |
+| **Recovery**                            | **100.00**                        | **99.31**                                   |
 
 #### HumanEval pass@1 scores
 | Metric                                  | ibm-granite/granite-3.1-8b-instruct             | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16 |
 |-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
-| HumanEval Pass@1                        | 71.00                             | 70.90                                      |
+| HumanEval Pass@1                        | 71.00                             | 70.50                                      |