Rename ggml-model-q4_0.bin to ggml-model-q4_KM.bin 841e783
nRuaif commited on
How to use Chat-Error/Blind-test02 with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-13b-hf")
model = PeftModel.from_pretrained(base_model, "Chat-Error/Blind-test02")