This model is an early release of an upcoming model for testing purposes. The format is ChatML. If you use this model let me know how it goes.
Training details:
- 1x RTX 4080
- Rank 64 RSLoRA
- 70 Hours runtime
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.14 |
| IFEval (0-Shot) | 51.24 |
| BBH (3-Shot) | 26.82 |
| MATH Lvl 5 (4-Shot) | 3.25 |
| GPQA (0-shot) | 6.15 |
| MuSR (0-shot) | 8.03 |
| MMLU-PRO (5-shot) | 19.38 |
- Downloads last month
- 18
Model tree for Dans-DiscountModels/Mistral-7b-v0.3-Test-E0.7
Base model
Dans-DiscountModels/mistral-7b-v0.3-ChatMLEvaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard51.240
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard26.820
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard3.250
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.150
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.030
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard19.380