Downloads · 30 days
53
0% of all-time downloads
dhmeltzer/llama-7b-SFT_ds_eli5_1024_r_64_alpha_16_merged
llama-7b-SFT_ds_eli5_1024_r_64_alpha_16_merged is a text generation model from dhmeltzer. Use it when you need the model to write or continue text. It is set up for transformers.
Downloads · 30 days
53
0% of all-time downloads
All-time downloads
53.4K
Public
Parameters
6.7B
40.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin13.5 GB · 50%
From the Hugging Face model README
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 43.25 |
| ARC (25-shot) | 53.41 |
| HellaSwag (10-shot) | 77.9 |
| MMLU (5-shot) | 43.56 |
| TruthfulQA (0-shot) | 40.81 |
| Winogrande (5-shot) | 74.59 |
| GSM8K (5-shot) | 5.08 |
| DROP (3-shot) | 7.37 |