How to use FormlessAI/Qwen2.5-3B-Instruct-DPO-TogetherAI with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "FormlessAI/Qwen2.5-3B-Instruct-DPO-TogetherAI")
https://huggingface.co/FormlessAI/Qwen2.5-3B-Instruct-DPO-TogetherAI/resolve/main/trainer_state.json
hf download hf://FormlessAI/Qwen2.5-3B-Instruct-DPO-TogetherAI/trainer_state.json
curl -L -o trainer_state.json https://huggingface.co/FormlessAI/Qwen2.5-3B-Instruct-DPO-TogetherAI/resolve/main/trainer_state.json
