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)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("chandar-lab/NeoBERT", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
bug with using Neobert for Sequence Classification
#9
by Romzzeess - opened
Hello, I have bug with using Neobert for Sequence Classification- i don't get back logits like in other models. Could you add in line "https://huggingface.co/chandar-lab/NeoBERT/blob/main/model.py#L381"
a code: "return_dict = return_dict if return_dict is not None else self.config.use_return_dict" like it is in other Sequence Classification model, for example microsoft/deberta-v3-base.(They also have this line here: https://github.com/huggingface/transformers/blob/main/src/transformers/models/deberta_v2/modeling_deberta_v2.py#L843)
Thanks
Lolalb changed discussion status to closed