Llama3.1-Flammades-70B
nbeerbower/Llama3.1-Gutenberg-Doppel-70B finetuned on flammenai/Date-DPO-NoAsterisks and jondurbin/truthy-dpo-v0.1.
Method
ORPO tuned with 2x H100 for 3 epochs.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 35.74 |
| IFEval (0-Shot) | 70.58 |
| BBH (3-Shot) | 52.55 |
| MATH Lvl 5 (4-Shot) | 13.37 |
| GPQA (0-shot) | 13.87 |
| MuSR (0-shot) | 22.35 |
| MMLU-PRO (5-shot) | 41.69 |
- Downloads last month
- -
Model tree for flammenai/Llama3.1-Flammades-70B
Base model
mlabonne/Hermes-3-Llama-3.1-70B-lorablated
Finetuned
nbeerbower/Llama3.1-Gutenberg-Doppel-70B
Datasets used to train flammenai/Llama3.1-Flammades-70B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard70.580
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard52.550
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard13.370
- acc_norm on GPQA (0-shot)Open LLM Leaderboard13.870
- acc_norm on MuSR (0-shot)Open LLM Leaderboard22.350
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard41.690