Llama3.1-Gutenberg-Doppel-70B
mlabonne/Hermes-3-Llama-3.1-70B-lorablated finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.
Method
ORPO tuned with 2x H100 for 3 epochs.
Thank you Schneewolf Labs for the compute.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 35.68 |
IFEval (0-Shot) | 70.92 |
BBH (3-Shot) | 52.56 |
MATH Lvl 5 (4-Shot) | 13.75 |
GPQA (0-shot) | 12.64 |
MuSR (0-shot) | 22.68 |
MMLU-PRO (5-shot) | 41.52 |
- Downloads last month
- 340
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for nbeerbower/Llama3.1-Gutenberg-Doppel-70B
Base model
mlabonne/Hermes-3-Llama-3.1-70B-lorablatedDatasets used to train nbeerbower/Llama3.1-Gutenberg-Doppel-70B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard70.920
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard52.560
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard13.750
- acc_norm on GPQA (0-shot)Open LLM Leaderboard12.640
- acc_norm on MuSR (0-shot)Open LLM Leaderboard22.680
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard41.520