Instructions to use chandar-lab/NeoBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chandar-lab/NeoBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="chandar-lab/NeoBERT", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("chandar-lab/NeoBERT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add feature-extraction pipeline tag
Verified signatureThis PR adds the `feature-extraction` pipeline tag to the model card metadata. This allows the model to be easily discoverable through the Hugging Face model hub.d6bef32
-
Minor changes for correct inference (#1)
Verified signature- Update AutoModel... in config.json (dd59cdc4b01d3a8ad2681ed0013ceebc31725bc5) - Add base_model_prefix="model" on PreTrainedModel (12e66dc10a87bfe0625eccf988d7e1a4f243bbdf) - Cast attention_mask to bool in SDPA (30e2384fbf7e72648008059a67882cee811cbfd8) - Tag this model as transformers-compatible (364b6518d26f4b5a6445cb7e350e49427a1cb2c0) - Specify that we don't want the token_type_ids from the tokenizer (05bfcead01ea0a78660206db4699db8f0791386a)d97a4ac -
Update README.md
Verified signaturec10259c -
Update README.md
Verified signaturea40107a -
Upload logo.jpeg
Verified signature6ca1698 -
Update README.md
Verified signature9e880d3 -
Upload tokenizer
Verified signaturef9eb7ee -
Upload NeoBERTLMHead
Verified signature4151e21 -
initial commit
Verified signature3f6fd5c