Downloads · 30 days
108
0% of all-time downloads
KnutJaegersberg/MistralInstructLongish
MistralInstructLongish is a text generation model from KnutJaegersberg. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
It was trained for like 3 epochs on a merger dataset of several instruction datasets, with partially longer instructions.
Downloads · 30 days
108
0% of all-time downloads
All-time downloads
59.4K
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
It was trained for like 3 epochs on a merger dataset of several instruction datasets, with partially longer instructions.
Alpaca Prompt Format:
### Instruction:
blablabla
### Input:
(optional)
### Response:
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 48.99 |
| ARC (25-shot) | 60.75 |
| HellaSwag (10-shot) | 81.86 |
| MMLU (5-shot) | 60.49 |
| TruthfulQA (0-shot) | 40.55 |
| Winogrande (5-shot) | 76.56 |
| GSM8K (5-shot) | 1.52 |
| DROP (3-shot) | 21.22 |