https://github.com/arjunravi26/ai_psychologist
Fine tune llama 2 model with mental health counseling data from huggingface
https://github.com/arjunravi26/ai_psychologist
accelerate bitsandbytes llama lora peft python qlora streamlit torch transformer
Last synced: 29 days ago
JSON representation
Fine tune llama 2 model with mental health counseling data from huggingface
- Host: GitHub
- URL: https://github.com/arjunravi26/ai_psychologist
- Owner: arjunravi26
- Created: 2025-06-02T12:44:38.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-02T12:57:20.000Z (about 1 year ago)
- Last Synced: 2025-10-17T11:08:36.522Z (8 months ago)
- Topics: accelerate, bitsandbytes, llama, lora, peft, python, qlora, streamlit, torch, transformer
- Language: Jupyter Notebook
- Homepage:
- Size: 14.5 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Psychologist Assistant — LLM Chatbot
This project is a **mental health–oriented chatbot** that simulates a psychologist's responses using a fine-tuned large language model (LLM). It supports both:
- High-end GPU usage with 4-bit quantized models (QLoRA)
- CPU usage for low-resource systems (no quantization)
It uses **Hugging Face Transformers**, **PEFT (LoRA)**, and **Streamlit** for the user interface.
---
## Features
- Simulates a supportive psychologist
- Interactive chat interface (Streamlit)
- Supports low-resource (CPU) and GPU systems
- Modular design: easy to swap models or fine-tune
---
## Setup
1. **Install dependencies**
```bash
pip install -r requirements.txt
streamlit run app.py
```