Instructions to use niksmer/ManiBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use niksmer/ManiBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="niksmer/ManiBERT")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("niksmer/ManiBERT") model = AutoModelForSequenceClassification.from_pretrained("niksmer/ManiBERT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from niksmer/ManiBERT: direct link, hf CLI and curl.
- Browser
- Download file 499 MB
-
https://huggingface.co/niksmer/ManiBERT/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://niksmer/ManiBERT/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/niksmer/ManiBERT/resolve/main/pytorch_model.bin
499 MB
- Xet hash:
- 8aaabf01bbd442113d501cce563bb90b30e34791b925df838abe30d27a247beb
- Size of remote file:
- 499 MB
- SHA256:
- e7d4791335c11d2435416416201e6dda03ad8598a4a092d9ef80274e4c8b0a95
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.