Instructions to use mole-code/llama_index-codegen-2B-mono-prefix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mole-code/llama_index-codegen-2B-mono-prefix with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mole-code/llama_index-codegen-2B-mono-prefix", dtype="auto") - Notebooks
- Google Colab
- Kaggle