ConvexAI/Luminex-72B-v0.1
This model is a fine-tuned version of abacusai/Smaug-72B-v0.1 on the Neural-DPO dataset
Evaluation Results
Coming Soon
Contamination Results
Coming Soon
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 66.15 |
| AI2 Reasoning Challenge (25-Shot) | 43.43 |
| HellaSwag (10-Shot) | 86.66 |
| MMLU (5-Shot) | 73.36 |
| TruthfulQA (0-shot) | 41.85 |
| Winogrande (5-shot) | 76.16 |
| GSM8k (5-shot) | 75.44 |
Model tree for ConvexAI/Luminex-72B-v0.1
Dataset used to train ConvexAI/Luminex-72B-v0.1
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard43.430
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard86.660
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard73.360
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard41.850
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard76.160
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard75.440