Submitted Models
Collection
This collection includes base phi3-mini A) DPO aligned B) SFT on ARC train split (3 epochs) C) Quantised version of B) using GPTQ. • 3 items • Updated
How to use cs552-mlp/phi3-dpo with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("unsloth/Phi-3-mini-4k-instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "cs552-mlp/phi3-dpo")Base model
unsloth/Phi-3-mini-4k-instruct-bnb-4bit