decem/Dionysus-Mistral-m3-v5 - A Fine-tuned Language Model
Model Details
- Developer: DECEM
- Fine-tuning Method: SFT
- Language: English
Prompting
Prompt Template for alpaca style
### Instruction:
<prompt> (without the <>)
### Response:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 63.14 |
| AI2 Reasoning Challenge (25-Shot) | 59.56 |
| HellaSwag (10-Shot) | 80.99 |
| MMLU (5-Shot) | 61.18 |
| TruthfulQA (0-shot) | 50.93 |
| Winogrande (5-shot) | 75.14 |
| GSM8k (5-shot) | 51.02 |
- Downloads last month
- 792
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 decem/Dionysus-Mistral-m3-v5
Spaces using decem/Dionysus-Mistral-m3-v5 6
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard59.560
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard80.990
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard61.180
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard50.930
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard75.140
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard51.020