Update README.md
Browse files
README.md
CHANGED
|
@@ -197,17 +197,17 @@ evalplus.evaluate \
|
|
| 197 |
|
| 198 |
| Metric | ibm-granite/granite-3.1-8b-instruct | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w8a8 |
|
| 199 |
|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
|
| 200 |
-
| ARC-Challenge (Acc-Norm, 25-shot) | 66.81 |
|
| 201 |
-
| GSM8K (Strict-Match, 5-shot) | 64.52 |
|
| 202 |
-
| HellaSwag (Acc-Norm, 10-shot) | 84.18 | 83.
|
| 203 |
-
| MMLU (Acc, 5-shot) | 65.52 | 65.
|
| 204 |
-
| TruthfulQA (MC2, 0-shot) | 60.57 | 60.
|
| 205 |
| Winogrande (Acc, 5-shot) | 80.19 | 79.87 |
|
| 206 |
-
| **Average Score** | **70.30** | **70.
|
| 207 |
-
| **Recovery** | **100.00** | **99.
|
| 208 |
|
| 209 |
#### HumanEval pass@1 scores
|
| 210 |
| Metric | ibm-granite/granite-3.1-8b-instruct | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w8a8 |
|
| 211 |
|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
|
| 212 |
-
| HumanEval Pass@1 | 71.00 |
|
| 213 |
|
|
|
|
| 197 |
|
| 198 |
| Metric | ibm-granite/granite-3.1-8b-instruct | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w8a8 |
|
| 199 |
|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
|
| 200 |
+
| ARC-Challenge (Acc-Norm, 25-shot) | 66.81 | 67.06 |
|
| 201 |
+
| GSM8K (Strict-Match, 5-shot) | 64.52 | 65.66 |
|
| 202 |
+
| HellaSwag (Acc-Norm, 10-shot) | 84.18 | 83.93 |
|
| 203 |
+
| MMLU (Acc, 5-shot) | 65.52 | 65.03 |
|
| 204 |
+
| TruthfulQA (MC2, 0-shot) | 60.57 | 60.02 |
|
| 205 |
| Winogrande (Acc, 5-shot) | 80.19 | 79.87 |
|
| 206 |
+
| **Average Score** | **70.30** | **70.26** |
|
| 207 |
+
| **Recovery** | **100.00** | **99.95** |
|
| 208 |
|
| 209 |
#### HumanEval pass@1 scores
|
| 210 |
| Metric | ibm-granite/granite-3.1-8b-instruct | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w8a8 |
|
| 211 |
|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
|
| 212 |
+
| HumanEval Pass@1 | 71.00 | 70.50 |
|
| 213 |
|