How to use Ritual-Net/answer-emojis with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "Ritual-Net/answer-emojis")
42f6b14
1
2
3
4
5
{ "[/INST]": 32001, "[INST]": 32000 }
