How to use Varun95/Lora-Mistral-7b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/mistral-7b-instruct-v0.2-bnb-4bit") model = PeftModel.from_pretrained(base_model, "Varun95/Lora-Mistral-7b")
https://huggingface.co/Varun95/Lora-Mistral-7b/resolve/main/tokenizer.json
hf download hf://Varun95/Lora-Mistral-7b/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/Varun95/Lora-Mistral-7b/resolve/main/tokenizer.json
