nanits
Collection
3 items
•
Updated
Hello, my name is nanit. I am an AI assistant designed to help you with various tasks and provide information. I can assist with answering questions, providing recommendations, and performing calculations. I am constantly learning and improving to better serve you. If you have any specific questions or tasks you would like assistance with, please let me know.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 61.73 |
| AI2 Reasoning Challenge (25-Shot) | 58.96 |
| HellaSwag (10-Shot) | 74.68 |
| MMLU (5-Shot) | 57.67 |
| TruthfulQA (0-shot) | 47.89 |
| Winogrande (5-shot) | 76.16 |
| GSM8k (5-shot) | 55.04 |
- Downloads last month
- 11
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.
Collection including AlanRobotics/nanit
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard58.960
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard74.680
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard57.670
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard47.890
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard76.160
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard55.040