Uploaded model
- Developed by: BarraHome
- License: apache-2.0
- Finetuned from model : BarraHome/zephyr-dpo-4bit
This mistral 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. | 59.99 |
| AI2 Reasoning Challenge (25-Shot) | 57.85 |
| HellaSwag (10-Shot) | 82.72 |
| MMLU (5-Shot) | 58.61 |
| TruthfulQA (0-shot) | 56.16 |
| Winogrande (5-shot) | 74.35 |
| GSM8k (5-shot) | 30.25 |
- Downloads last month
- 999
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 BarraHome/zephyr-dpo-v2
Datasets used to train BarraHome/zephyr-dpo-v2
Spaces using BarraHome/zephyr-dpo-v2 5
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard57.850
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard82.720
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard58.610
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard56.160
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard74.350
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard30.250