Uploaded model
- Developed by: Daemontatox
- License: apache-2.0
- Finetuned from model : unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here! Summarized results can be found here!
| Metric | Value (%) |
|---|---|
| Average | 30.98 |
| IFEval (0-Shot) | 66.39 |
| BBH (3-Shot) | 34.94 |
| MATH Lvl 5 (4-Shot) | 19.79 |
| GPQA (0-shot) | 10.18 |
| MuSR (0-shot) | 18.60 |
| MMLU-PRO (5-shot) | 35.97 |
- Downloads last month
- 27
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Daemontatox/Zirel-7B-Math
Evaluation results
- averaged accuracy on IFEval (0-Shot)Open LLM Leaderboard66.390
- normalized accuracy on BBH (3-Shot)test set Open LLM Leaderboard34.940
- exact match on MATH Lvl 5 (4-Shot)test set Open LLM Leaderboard19.790
- acc_norm on GPQA (0-shot)Open LLM Leaderboard10.180
- acc_norm on MuSR (0-shot)Open LLM Leaderboard18.600
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard35.970