Instructions to use UT/BMW with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UT/BMW with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="UT/BMW")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("UT/BMW") model = AutoModelForSequenceClassification.from_pretrained("UT/BMW", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from UT/BMW: direct link, hf CLI and curl.
- Browser
- Download file 1.11 GB
-
https://huggingface.co/UT/BMW/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://UT/BMW/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/UT/BMW/resolve/main/pytorch_model.bin
1.11 GB
- Xet hash:
- 865d8a728b704af69b0de535ce94a971e00261878d14c5c0365177f5539c992c
- Size of remote file:
- 1.11 GB
- SHA256:
- 1d12a54ea38ed6d3abed6f2eb731e8512bb9037d858be2c84e2522de565e8d88
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.