Update README.md
Browse files
README.md
CHANGED
@@ -205,12 +205,12 @@ evalplus.evaluate \
|
|
205 |
|
206 |
| Metric | ibm-granite/granite-3.1-8b-instruct | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16 |
|
207 |
|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
|
208 |
-
| IFEval (Inst Level Strict Acc, 0-shot)| | 73.14 |
|
209 |
| BBH (Acc-Norm, 3-shot) | 53.19 | 51.52 |
|
210 |
| Math-Hard (Exact-Match, 4-shot) | 14.77 | 16.66 |
|
211 |
| GPQA (Acc-Norm, 0-shot) | 31.76 | 29.91 |
|
212 |
| MUSR (Acc-Norm, 0-shot) | 46.01 | 45.75 |
|
213 |
-
| MMLU-Pro (Acc, 5-shot) |
|
214 |
| **Average Score** | **42.61** | **41.87** |
|
215 |
| **Recovery** | **100.00** | **98.26** |
|
216 |
|
|
|
205 |
|
206 |
| Metric | ibm-granite/granite-3.1-8b-instruct | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16 |
|
207 |
|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
|
208 |
+
| IFEval (Inst Level Strict Acc, 0-shot)| 74.01 | 73.14 |
|
209 |
| BBH (Acc-Norm, 3-shot) | 53.19 | 51.52 |
|
210 |
| Math-Hard (Exact-Match, 4-shot) | 14.77 | 16.66 |
|
211 |
| GPQA (Acc-Norm, 0-shot) | 31.76 | 29.91 |
|
212 |
| MUSR (Acc-Norm, 0-shot) | 46.01 | 45.75 |
|
213 |
+
| MMLU-Pro (Acc, 5-shot) | 35.81 | 34.23 |
|
214 |
| **Average Score** | **42.61** | **41.87** |
|
215 |
| **Recovery** | **100.00** | **98.26** |
|
216 |
|