Uploaded model
- Developed by: FlofloB
- License: apache-2.0
- Finetuned from model : unsloth/qwen2.5-0.5b-instruct-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
| Metric | Value |
|---|---|
| Avg. | 7.92 |
| IFEval (0-Shot) | 28.69 |
| BBH (3-Shot) | 8.13 |
| MATH Lvl 5 (4-Shot) | 0.00 |
| GPQA (0-shot) | 3.13 |
| MuSR (0-shot) | 1.42 |
| MMLU-PRO (5-shot) | 6.17 |
- Downloads last month
- 878
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
Dataset used to train FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard28.690
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard8.130
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard3.130
- acc_norm on MuSR (0-shot)Open LLM Leaderboard1.420
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard6.170