|
Quantization made by Richard Erkhov. |
|
|
|
[Github](https://github.com/RichardErkhov) |
|
|
|
[Discord](https://discord.gg/pvy7H8DZMG) |
|
|
|
[Request more models](https://github.com/RichardErkhov/quant_request) |
|
|
|
|
|
GPTNeo350M-Instruct-SFT - bnb 8bits |
|
- Model creator: https://huggingface.co/SummerSigh/ |
|
- Original model: https://huggingface.co/SummerSigh/GPTNeo350M-Instruct-SFT/ |
|
|
|
|
|
|
|
|
|
Original model description: |
|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_SummerSigh__GPTNeo350M-Instruct-SFT) |
|
|
|
| Metric | Value | |
|
|-----------------------|---------------------------| |
|
| Avg. | 27.03 | |
|
| ARC (25-shot) | 25.94 | |
|
| HellaSwag (10-shot) | 38.55 | |
|
| MMLU (5-shot) | 25.76 | |
|
| TruthfulQA (0-shot) | 45.25 | |
|
| Winogrande (5-shot) | 50.2 | |
|
| GSM8K (5-shot) | 0.3 | |
|
| DROP (3-shot) | 3.24 | |
|
|
|
|
|
|