from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_id = "microsoft/Phi-3-mini-4k-instruct"
adapter_id = "TUO_USERNAME/phi3-mr-lora-fixed-v3"

tokenizer = AutoTokenizer.from_pretrained(base_id)

base_model = AutoModelForCausalLM.from_pretrained(
    base_id,
    load_in_4bit=True,
    device_map="auto",
    torch_dtype="auto",
)

model = PeftModel.from_pretrained(base_model, adapter_id, device_map="auto")

FBondi/phi3-mr-lora-weights

phi3-mr-lora-fixed-v3 (LoRA adapter)

Base model

Usage

FBondi/
phi3-mr-lora-weights