Osiria "Air" Series ☁
Collection
This collection is composed of compact and lightweight models, which are ideal for low-resource settings • 6 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("osiria/minilm-l12-h384-italian-cased")
model = AutoModelForMaskedLM.from_pretrained("osiria/minilm-l12-h384-italian-cased", device_map="auto")Quick Links
Model: MiniLM
Lang: IT
Model description
This is a MiniLMv2 [1] model for the Italian language, obtained using mMiniLMv2 (L12xH384 mMiniLMv2) as a starting point and focusing it on the Italian language by modifying the embedding layer (as in [2], computing document-level frequencies over the Wikipedia dataset)
The resulting model has 33M parameters, a vocabulary of 30.498 tokens, and a size of ~130 MB.
References
[1] https://arxiv.org/abs/2012.15828
[2] https://arxiv.org/abs/2010.05609
License
The model is released under MIT license
- Downloads last month
- 25
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="osiria/minilm-l12-h384-italian-cased")