TinyLlama/TinyLlama-1.1B-Chat-v1.0 dpo finetuned on the argilla/distilabel-intel-orca-dpo-pairs dataset, which is the distilled version of https://huggingface.co/datasets/Intel/orca_dpo_pairs
GGUF Version: To be added Exllama Version: To be added
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 37.17 |
| AI2 Reasoning Challenge (25-Shot) | 36.18 |
| HellaSwag (10-Shot) | 61.15 |
| MMLU (5-Shot) | 25.09 |
| TruthfulQA (0-shot) | 38.05 |
| Winogrande (5-shot) | 60.85 |
| GSM8k (5-shot) | 1.67 |
- Downloads last month
- 2,318
Dataset used to train eren23/DistiLabelOrca-TinyLLama-1.1B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard36.180
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard61.150
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard25.090
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard38.050
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard60.850
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard1.670