Instructions to use slone/bert-small-from-nllb-200-raw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use slone/bert-small-from-nllb-200-raw with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="slone/bert-small-from-nllb-200-raw")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("slone/bert-small-from-nllb-200-raw") model = AutoModel.from_pretrained("slone/bert-small-from-nllb-200-raw", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from slone/bert-small-from-nllb-200-raw: direct link, hf CLI and curl.
- Browser
- Download file 604 MB
-
https://huggingface.co/slone/bert-small-from-nllb-200-raw/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://slone/bert-small-from-nllb-200-raw/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/slone/bert-small-from-nllb-200-raw/resolve/main/pytorch_model.bin
604 MB
- Xet hash:
- c7528943b8126d04657e5795c961fbb8513372c0b190ac3fdb39640823c4e1f1
- Size of remote file:
- 604 MB
- SHA256:
- c25b23ad1c1e70325501626b0149a2b8aa675b810c75656a91cfeafb35d04404
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.