Instructions to use facebook/nllb-200-distilled-1.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/nllb-200-distilled-1.3B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="facebook/nllb-200-distilled-1.3B")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-1.3B") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-1.3B") - Notebooks
- Google Colab
- Kaggle
Difference between distilled and the original?
#1
by ghosthamlet - opened
Thanks for this great model.
The original model: https://huggingface.co/facebook/nllb-200-1.3B has a same size file pytorch_model.bin as this distilled version,
then what is the difference between these two model?
As I understand it (from the paper) this is a 1.3B parameters model distilled from the full 54B NLLB-200 model. it gives better results then 1.3 B dense (Table 41 in the paper).
Thanks for the reply.
ghosthamlet changed discussion status to closed