cyril21/breakfree-dialo-lora

BreakFree DialoGPT LoRA Adapter

This repository contains LoRA adapter weights fine-tuned on rehabilitation and mental health support dialogues. It is intended to be used with the base model microsoft/DialoGPT-medium.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_id = "microsoft/DialoGPT-medium"
adapter_id = "cyril21/breakfree-dialo-lora"

tokenizer = AutoTokenizer.from_pretrained(base_id)
if tokenizer.pad_token is None:
    tokenizer.pad_token = tokenizer.eos_token

base_model = AutoModelForCausalLM.from_pretrained(base_id)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()

prompt = "User: Hello\nAssistant:"
inputs = tokenizer(prompt, return_tensors="pt")
with torch.no_grad():
    output = model.generate(
        **inputs,
        max_new_tokens=80,
        do_sample=True,
        top_p=0.9,
        temperature=0.8,
        pad_token_id=tokenizer.eos_token_id,
    )

print(tokenizer.decode(output[0], skip_special_tokens=True))

Training Data

Fine-tuned on a local rehabilitation dialogue dataset. A public dataset repo is provided separately.

Limitations

This model is intended for supportive, non-clinical conversation. It is not a substitute for professional medical or mental health advice.

Model Card Contact

[More Information Needed]

Framework versions

• PEFT 0.17.1