Update README.md
Browse files
README.md
CHANGED
|
@@ -28,10 +28,6 @@ widget:
|
|
| 28 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/5f0b462819cb630495b814d7/DVA4MnFUs3UHBnTrX9jG6.png" style="max-width: 550px; height: auto;">
|
| 29 |
</div>
|
| 30 |
|
| 31 |
-
## Please note:
|
| 32 |
-
|
| 33 |
-
This model is currently training, the weights available at the moment are taken from the checkpoint at **60K steps out of 590K**. You can monitor the training on [Wandb](https://wandb.ai/riccorl/minerva-llms).
|
| 34 |
-
|
| 35 |
# Model Card for Minerva-7B-base-v1.0
|
| 36 |
|
| 37 |
Minerva is the first family of **LLMs pretrained from scratch on Italian** developed by [Sapienza NLP](https://nlp.uniroma1.it)
|
|
|
|
| 28 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/5f0b462819cb630495b814d7/DVA4MnFUs3UHBnTrX9jG6.png" style="max-width: 550px; height: auto;">
|
| 29 |
</div>
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
# Model Card for Minerva-7B-base-v1.0
|
| 32 |
|
| 33 |
Minerva is the first family of **LLMs pretrained from scratch on Italian** developed by [Sapienza NLP](https://nlp.uniroma1.it)
|