Model Card for cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
try to improve mistralai/Mixtral-8x7B-Instruct-v0.1 by DPO training
Metrics improved by Truthful DPO traingin after 100 steps
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 73.44 |
| AI2 Reasoning Challenge (25-Shot) | 69.80 |
| HellaSwag (10-Shot) | 87.83 |
| MMLU (5-Shot) | 71.05 |
| TruthfulQA (0-shot) | 69.18 |
| Winogrande (5-shot) | 81.37 |
| GSM8k (5-shot) | 61.41 |
- Downloads last month
- 659
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.
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard69.800
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard87.830
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard71.050
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard69.180
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard81.370
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard61.410