Model Card for Social RLHF

Model Details

This model is a fine-tuned version of Qwen2.5-0.5B-Instruct on the ProlificAI/social-reasoning-rlhf dataset using ORPO. The primary objective was to experiment with Reinforcement Learning from Human Feedback (RLHF) via ORPO, focusing on preference alignment.

Model Description

• Language(s) (NLP): English
• License: MIT
• Finetuned from model: unsloth/Qwen2.5-0.5B-Instruct
• Fine-tuning Method: ORPO (Offline Reinforcement Preference Optimization)
• Dataset: ProlificAI/social-reasoning-rlhf

How to Get Started with the Model

Use the code below to get started with the model.

from huggingface_hub import login
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

login(token="")

tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen2.5-0.5B-Instruct",)
base_model = AutoModelForCausalLM.from_pretrained(
    "unsloth/Qwen2.5-0.5B-Instruct",
    device_map={"": 0}, token=""
)

model = PeftModel.from_pretrained(base_model,"khazarai/Social-RLHF")


prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""


inputs = tokenizer(
    [
        prompt.format(
            "You are an AI assistant that helps people find information",
            "A stranger shares private information with you on public transportation. How might you respond sensitively?", 
            "",  
        )
    ],
    return_tensors="pt",
).to("cuda")


from transformers import TextStreamer

text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=512)

Framework versions

• PEFT 0.17.1