Llama 3.1 8B Fact-Check Reply

Published by @verifai_dev · Community adapter

Generates sourced rebuttals to factual claims. Identifies verifiable assertions, suggests authoritative sources, and produces polite but firm corrections.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/llama31-8b-debate-reply-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.43
• vLLM