Instructions to use titan087/Mistral-7B-Instruct-v0.2_2gpu-TRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use titan087/Mistral-7B-Instruct-v0.2_2gpu-TRT with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("titan087/Mistral-7B-Instruct-v0.2_2gpu-TRT", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K