Instructions to use blackmount8/falcon-7b-instruct-ct2-int8_float16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use blackmount8/falcon-7b-instruct-ct2-int8_float16 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("blackmount8/falcon-7b-instruct-ct2-int8_float16", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Sample Code for int8_float16
#1 opened over 2 years ago
by
lazyDataScientist