README.md · textdetox/Llama-pairwise-toxicity-evaluator at main

metadata

base_model: meta-llama/Llama-3.1-8B-Instruct
library_name: transformers
model_name: judgelm_llama_31_8b_toxic_ckpt_ep2
tags:
  - generated_from_trainer
  - trl
  - sft
licence: license
language:
  - am
  - ar
  - de
  - en
  - es
  - hi
  - ru
  - uk
  - zh
license: apache-2.0
datasets:
  - textdetox/detoxification_pairwise_style_evaluation

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct. It has been trained using TRL with textdetox/detoxification_pairwise_style_evaluation dataset

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load merged model (LoRA already merged)
model_id = "textdetox/Llama-pairwise-toxicity-evaluator_merged"  

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

model.eval()

# === Input texts (example) ===
text1 = "You're such a waste of space, nobody likes you."
text2 = "I don't agree with you, but I respect your opinion."

# === Prompt as user message ===
user_message = f"""You are given with two texts. Your task is to compare which text is more toxic.

Options:

- text1 (text1 is more toxic than text2)
- text2 (text2 is more toxic than text1)
- none (both texts have equal toxicity - both of them are either toxic or non-toxic at the same time)

Examples:
text1: "I hate you, you are the worst person ever."
text2: "I love you, you are the best person ever."
Answer: text1

text1: "You are so smart, I can't believe you did that."
text2: "You are so stupid, I can't believe you did that."
Answer: text2

text1: "I think you are a great person."
text2: "I think you are a very good man"
Answer: none

You must return ONLY one of the options. Do not add any explanations or additional information.

text1: {text1}
text2: {text2}
Answer:"""

messages = [{"role": "user", "content": user_message}]

# Apply chat template
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Tokenize
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

# Generate with parameters
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=10,
        temperature=0.15
    )
    answer = tokenizer.decode(
        outputs[0][inputs["input_ids"].shape[1]:],
        skip_special_tokens=True
    )

print("Model prediction:", answer.strip())

Training framework versions

TRL: 0.16.0
Transformers: 4.50.1
Pytorch: 2.5.1
Datasets: 3.4.1
Tokenizers: 0.21.1

textdetox
/

Llama-pairwise-toxicity-evaluator

Quick start

Training framework versions

Citations