Update README.md
Browse files
README.md
CHANGED
|
@@ -59,7 +59,7 @@ vLLM also supports OpenAI-compatible serving. See the [documentation](https://do
|
|
| 59 |
## Evaluation
|
| 60 |
|
| 61 |
The model was evaluated on popular reasoning tasks (AIME 2024, MATH-500, GPQA-Diamond) via [LightEval](https://github.com/huggingface/open-r1).
|
| 62 |
-
For reasoning evaluations, we estimate pass@1 based on 10 runs with different seeds.
|
| 63 |
|
| 64 |
|
| 65 |
### Accuracy
|
|
|
|
| 59 |
## Evaluation
|
| 60 |
|
| 61 |
The model was evaluated on popular reasoning tasks (AIME 2024, MATH-500, GPQA-Diamond) via [LightEval](https://github.com/huggingface/open-r1).
|
| 62 |
+
For reasoning evaluations, we estimate pass@1 based on 10 runs with different seeds, `temperature=0.6`, `top_p=0.95` and `max_new_tokens=65536`.
|
| 63 |
|
| 64 |
|
| 65 |
### Accuracy
|