Instructions to use Vishal24/llama2-full-aplacha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Vishal24/llama2-full-aplacha with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Vishal24/llama2-7B-base") model = PeftModel.from_pretrained(base_model, "Vishal24/llama2-full-aplacha") - Notebooks
- Google Colab
- Kaggle
Ctrl+K