RoleBeagle-11B
A DPO-finetune from vicgalle/CarbonBeagle-11B-truthy over a subset of OpenHermesPreferences containting RP conversations. It keeps most of the intelligence from CarbonBeagle-11B, and hopefuly can role-play better.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 76.06 |
| AI2 Reasoning Challenge (25-Shot) | 72.35 |
| HellaSwag (10-Shot) | 89.77 |
| MMLU (5-Shot) | 66.35 |
| TruthfulQA (0-shot) | 77.92 |
| Winogrande (5-shot) | 84.06 |
| GSM8k (5-shot) | 65.88 |
- Downloads last month
- 2,231
Dataset used to train vicgalle/RoleBeagle-11B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard72.350
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.770
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard66.350
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard77.920
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard84.060
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard65.880