ReWiz
Collection
The ReWiz series is based on a subset of data from 3 different data sets, which has been used for fine tuning.
•
13 items
•
Updated
•
1
Prompt format
Use an alpaca-style prompt template for best results.
Uploaded model
- Developed by: theprint
- License: apache-2.0
- Finetuned from model : unsloth/meta-llama-3.1-8b-bnb-4bit
This llama 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. | 15.68 |
| IFEval (0-Shot) | 23.73 |
| BBH (3-Shot) | 23.77 |
| MATH Lvl 5 (4-Shot) | 4.53 |
| GPQA (0-shot) | 7.05 |
| MuSR (0-shot) | 9.34 |
| MMLU-PRO (5-shot) | 25.67 |
- Downloads last month
- 308
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.
Collection including theprint/ReWiz-Llama-3.1-8B-v2
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard23.730
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard23.770
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard4.530
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.050
- acc_norm on MuSR (0-shot)Open LLM Leaderboard9.340
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard25.670