metadata
license: other
llama2-13b-megacode2-oasst
Prompt template
chatml format is used: "<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n"
Multi-line:
<|im_start|>user
{user prompt}<|im_end|>
<|im_start|>assistant
{Assistant answer}<|im_end|>
Credits & Special Thanks
- Compute was generously sponsored by the eplf Machine Learning and Optimization Laboratory
- The open-source epfLLM/Megatron-LLM trainer was used for fine-tuning.
- rombodawg curated and published LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
- andreaskoepf prepared & orchestrated the training.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 49.61 |
| ARC (25-shot) | 60.67 |
| HellaSwag (10-shot) | 81.93 |
| MMLU (5-shot) | 57.38 |
| TruthfulQA (0-shot) | 47.85 |
| Winogrande (5-shot) | 76.16 |
| GSM8K (5-shot) | 15.54 |
| DROP (3-shot) | 7.74 |