EleanorZzz/CMV_Qwen2.5-7B-Instruct_BC

Behavior Cloning Generator for Persuasive Argumentation

LoRA adapter fine-tuned on ChangeMyView data for persuasive argument generation.

Base Model

Qwen/Qwen2.5-7B-Instruct

Training

Supervised fine-tuning (behavior cloning) on Delta-awarded CMV responses using LoRA.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct", device_map="auto")
model = PeftModel.from_pretrained(base, "EleanorZzz/CMV_Qwen2.5-7B-Instruct_BC")
tokenizer = AutoTokenizer.from_pretrained("EleanorZzz/CMV_Qwen2.5-7B-Instruct_BC")

Project

CS6120 Group 12 — Fine-tuning Language Models for Persuasive Argumentation