Model Merge Parameters
Base model: meta-llama/Meta-Llama-3-8B-Instruct Models: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct DeepMount00/Llama-3-8b-Ita nbeerbower/llama-3-gutenberg-8B jpacifico/French-Alpaca-Llama3-8B-Instruct-v1.0 meta-llama/Meta-Llama-3-8B-Instruct Merge method: breadcrumbs Random seed: 42 density: 0.5 gamma: 0.01 normalize: true weight: 1.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.38 |
| IFEval (0-Shot) | 32.04 |
| BBH (3-Shot) | 27.67 |
| MATH Lvl 5 (4-Shot) | 0.00 |
| GPQA (0-shot) | 6.94 |
| MuSR (0-shot) | 23.62 |
| MMLU-PRO (5-shot) | 26.05 |
- Downloads last month
- 6
Inference API (serverless) is not available, repository is disabled.
Model tree for johnsutor/Llama-3-8B-Instruct_breadcrumbs-density-0.5-gamma-0.01
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard32.040
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard27.670
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.940
- acc_norm on MuSR (0-shot)Open LLM Leaderboard23.620
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard26.050