Finetune of CultriX/MistralTrix-v1 on Symbolic Logic content from Lewis Carrol (at a very low learning rate because of the very small dataset - I'm just experimenting and have no idea if this was effective at changing the model output).
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 73.33 |
| AI2 Reasoning Challenge (25-Shot) | 72.53 |
| HellaSwag (10-Shot) | 88.34 |
| MMLU (5-Shot) | 65.26 |
| TruthfulQA (0-shot) | 70.93 |
| Winogrande (5-shot) | 80.66 |
| GSM8k (5-shot) | 62.24 |
- Downloads last month
- 690
Inference API (serverless) is not available, repository is disabled.
Dataset used to train ryandt/MusingCaterpillar
Spaces using ryandt/MusingCaterpillar 11
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard72.530
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard88.340
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.260
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard70.930
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard80.660
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard62.240