Vision/multimodal capabilities:
If you want to use vision functionality:
- You must use the latest versions of Koboldcpp.
To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo.
- You can load the mmproj by using the corresponding section in the interface:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 69.79 |
| AI2 Reasoning Challenge (25-Shot) | 67.58 |
| HellaSwag (10-Shot) | 86.03 |
| MMLU (5-Shot) | 64.79 |
| TruthfulQA (0-shot) | 59.58 |
| Winogrande (5-shot) | 79.64 |
| GSM8k (5-shot) | 61.11 |