Instructions to use behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_allWrong2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_allWrong2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Trelis/Llama-2-7b-chat-hf-sharded-bf16") model = PeftModel.from_pretrained(base_model, "behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_allWrong2") - Notebooks
- Google Colab
- Kaggle