Instructions to use prav719/DeepSeek-R1-Distill-Qwen-32B-flash-attention-2_H100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prav719/DeepSeek-R1-Distill-Qwen-32B-flash-attention-2_H100 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prav719/DeepSeek-R1-Distill-Qwen-32B-flash-attention-2_H100", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 3a624026d0b83a5a4485456977114d71554b40238967134c35b442b4888a670a
- Size of remote file:
- 5.62 kB
- SHA256:
- e6562d1ca1661e33e8b3edb2dfd1d47cc4d5ebf08e2b3a71afb0fd2dcd4ea4ca
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.