How to use vincentoh/codellama-34b-alpaca-instruct with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/codellama-34b-bnb-4bit") model = PeftModel.from_pretrained(base_model, "vincentoh/codellama-34b-alpaca-instruct")
https://huggingface.co/vincentoh/codellama-34b-alpaca-instruct/resolve/main/tokenizer.json
hf download hf://vincentoh/codellama-34b-alpaca-instruct/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/vincentoh/codellama-34b-alpaca-instruct/resolve/main/tokenizer.json
