Instructions to use Composio/mixtral_tensorrt_a100_tp2_w2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Composio/mixtral_tensorrt_a100_tp2_w2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Composio/mixtral_tensorrt_a100_tp2_w2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download llama_float16_tp2_rank0.engine from Composio/mixtral_tensorrt_a100_tp2_w2: direct link, hf CLI and curl.
- Browser
- Download file 46.8 GB
-
https://huggingface.co/Composio/mixtral_tensorrt_a100_tp2_w2/resolve/main/llama_float16_tp2_rank0.engine
- Command line
-
hf download hf://Composio/mixtral_tensorrt_a100_tp2_w2/llama_float16_tp2_rank0.engine
-
curl -L -o llama_float16_tp2_rank0.engine https://huggingface.co/Composio/mixtral_tensorrt_a100_tp2_w2/resolve/main/llama_float16_tp2_rank0.engine
46.8 GB
- Xet hash:
- b99e811ccf0dba89e7da71053c25fbc5e59f25aac17d9ca789e56f7cb1fc2d6e
- Size of remote file:
- 46.8 GB
- SHA256:
- 0d97601fd6a5d74aad00373ef5182f9273d1a0efde1f357905cfacecb6c08e1a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.