Instructions to use facebook/nllb-200-distilled-600M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/nllb-200-distilled-600M 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-600M")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Translation Issue with Certain Words Using facebook/nllb-200-distilled-600M Model
#35
by ltkien2003 - opened
I'm currently using the facebook/nllb-200-distilled-600M translation model for a project, and I've encountered an issue where certain words are not being translated correctly. For example, the phrase "I'm not sure" appears to be untranslated or incorrectly translated in some cases.