Instructions to use underactuated/opt-350m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use underactuated/opt-350m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="underactuated/opt-350m")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("underactuated/opt-350m") model = AutoModel.from_pretrained("underactuated/opt-350m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from underactuated/opt-350m: direct link, hf CLI and curl.
- Browser
- Download file 1.32 GB
-
https://huggingface.co/underactuated/opt-350m/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://underactuated/opt-350m/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/underactuated/opt-350m/resolve/main/pytorch_model.bin
1.32 GB
- Xet hash:
- 3c017a2f27487ebb185c21ad829473d24f2bcec6cb6f6d95dbd35e56cec809bc
- Size of remote file:
- 1.32 GB
- SHA256:
- 92e4e593df45c94bf5f6be867f07652fee78eec7f476d349ba2875d139c75fbd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.