ReWiz
Collection
The ReWiz series is based on a subset of data from 3 different data sets, which has been used for fine tuning.
•
11 items
•
Updated
•
1
Uploaded model
- Developed by: theprint
- License: apache-2.0
- Finetuned from model : unsloth/qwen2.5-14b-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. | 29.64 |
| IFEval (0-Shot) | 27.85 |
| BBH (3-Shot) | 44.86 |
| MATH Lvl 5 (4-Shot) | 26.89 |
| GPQA (0-shot) | 17.34 |
| MuSR (0-shot) | 15.44 |
| MMLU-PRO (5-shot) | 45.47 |
- Downloads last month
- 541
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 theprint/ReWiz-Qwen-2.5-14B
Collection including theprint/ReWiz-Qwen-2.5-14B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard27.850
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard44.860
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard26.890
- acc_norm on GPQA (0-shot)Open LLM Leaderboard17.340
- acc_norm on MuSR (0-shot)Open LLM Leaderboard15.440
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard45.470