Downloads · 30 days
57
4% of all-time downloads
vinhood/chefberto-italian-cased
chefberto-italian-cased is a fill-mask model from vinhood. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
chefberto-italian-cased is a BERT model obtained by MLM adaptive-tuning bert-base-italian-xxl-cased on Italian cooking recipes, approximately 50k sentences (2.6M words).
Downloads · 30 days
57
4% of all-time downloads
All-time downloads
1.6K
Public
Repo size
1.8 GB
Likes
0
Public
Click a slice to open those files.
.bin443 MB · 100%
From the Hugging Face model README
chefberto-italian-cased is a BERT model obtained by MLM adaptive-tuning bert-base-italian-xxl-cased on Italian cooking recipes, approximately 50k sentences (2.6M words).
Author: Cristiano De Nobili (@denocris on Twitter, LinkedIn) for VINHOOD.
<p> <img src="https://drive.google.com/uc?export=view&id=1u5aY2wKu-X5DAzbOq7rsgGFW5_lGUAQn" width="400"> </br> </p>Test set: 9k sentences about food.
| Model | Perplexity |
|---|---|
| chefberto-italian-cased | 1.84 |
| bert-base-italian-xxl-cased | 2.85 |
from transformers import AutoModel, AutoTokenizer
model_name = "vinhood/chefberto-italian-cased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)