Instructions to use JustFrederik/nllb-200-distilled-600M-ct2-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JustFrederik/nllb-200-distilled-600M-ct2-int8 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="JustFrederik/nllb-200-distilled-600M-ct2-int8")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JustFrederik/nllb-200-distilled-600M-ct2-int8", dtype="auto") - Notebooks
- Google Colab
- Kaggle
https://huggingface.co/facebook/nllb-200-distilled-600M
ct2-transformers-converter --model facebook/nllb-200-distilled-600M --quantization int8 --output_dir converted/nllb-200-distilled-600M-ct2-int8
- Downloads last month
- 546