19 lines
676 B
Markdown
19 lines
676 B
Markdown
# Stanford Alpaca
|
|
|
|
This is a replica of Alpaca by Stanford' tatsu
|
|
|
|
Trained using the original instructions with a minor modification in FSDP mode
|
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
|
|
| Metric | Value |
|
|
|-----------------------|---------------------------|
|
|
| Avg. | 41.96 |
|
|
| ARC (25-shot) | 52.3 |
|
|
| HellaSwag (10-shot) | 77.09 |
|
|
| MMLU (5-shot) | 41.6 |
|
|
| TruthfulQA (0-shot) | 37.58 |
|
|
| Winogrande (5-shot) | 69.46 |
|
|
| GSM8K (5-shot) | 1.44 |
|
|
| DROP (3-shot) | 14.23 |
|