Instructions to use Composio/mixtral_tensorrt_h100_tp2_w2_nvlink with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Composio/mixtral_tensorrt_h100_tp2_w2_nvlink with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Composio/mixtral_tensorrt_h100_tp2_w2_nvlink", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 7f33b56011a0d2bbf0bc3cd6e2f9a63f923855319985c859ca23b2adabbdcc2f
- Size of remote file:
- 46.8 GB
- SHA256:
- aed34654d99553144b91a2310ee8bc16f8d1109a65db6a74f56257db2b64ce2e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.