Instructions to use facebook/nllb-200-3.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/nllb-200-3.3B 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-200-3.3B")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-3.3B") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-3.3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from facebook/nllb-200-3.3B: direct link, hf CLI and curl.
- Browser
- Download file 17.3 MB
-
https://huggingface.co/facebook/nllb-200-3.3B/resolve/refs%2Fpr%2F10/tokenizer.json
- Command line
-
hf download hf://facebook/nllb-200-3.3B@refs/pr/10/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/facebook/nllb-200-3.3B/resolve/refs%2Fpr%2F10/tokenizer.json
17.3 MB
- Xet hash:
- 0202f54e596c03be98c5a537e9214967476071dce868ac20a7a42ad57fdd1f7b
- Size of remote file:
- 17.3 MB
- SHA256:
- e316b82de11d0f951f370943b3c438311629547285129b0b81dadabd01bca665
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.