Instructions to use kejian/debug-pt-conditional with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kejian/debug-pt-conditional with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("kejian/debug-pt-conditional") model = AutoModel.from_pretrained("kejian/debug-pt-conditional", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-10/pytorch_model.bin from kejian/debug-pt-conditional: direct link, hf CLI and curl.
- Browser
- Download file 457 MB
-
https://huggingface.co/kejian/debug-pt-conditional/resolve/main/checkpoint-10/pytorch_model.bin
- Command line
-
hf download hf://kejian/debug-pt-conditional/checkpoint-10/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/kejian/debug-pt-conditional/resolve/main/checkpoint-10/pytorch_model.bin
457 MB
- Xet hash:
- 4dd8cc432b4db4a3365fd4e5b42d7c5279117944848e584a1963998c36a6f6c1
- Size of remote file:
- 457 MB
- SHA256:
- cbd7462249e492f6f210a7658d1c633831d667aa3832213850dbe1172d70118b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.