metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: GeneZC/MiniChat-1.5-3B
model-index:
- name: smol-3b
results: []
smol-3b
See how open weights instead of open source feel like!
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 50.27 |
| AI2 Reasoning Challenge (25-Shot) | 46.33 |
| HellaSwag (10-Shot) | 68.23 |
| MMLU (5-Shot) | 46.33 |
| TruthfulQA (0-shot) | 50.73 |
| Winogrande (5-shot) | 65.35 |
| GSM8k (5-shot) | 24.64 |