1.3B test of two Cinder models merged layers 1-22 and 18-22, trained on math and step by step reasoning. Model Overview Cinder is an AI chatbot tailored for engaging users in scientific and educational conversations, offering companionship, and sparking imaginative exploration. It is built on the TinyLlama 1.1B parameter model and trained on a unique combination of datasets. Testing on Reason-with-cinder dataset.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 35.84 |
| AI2 Reasoning Challenge (25-Shot) | 32.51 |
| HellaSwag (10-Shot) | 55.85 |
| MMLU (5-Shot) | 26.61 |
| TruthfulQA (0-shot) | 35.59 |
| Winogrande (5-shot) | 62.12 |
| GSM8k (5-shot) | 2.35 |