You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Mental Health AI Chatbot

Overview

This AI-powered chatbot provides emotional support and mental health guidance through context-aware conversations. It is fine-tuned on mental health counseling conversations to ensure compassionate and relevant responses.

Features

  • Emotion Detection & Sentiment Analysis β†’ Adjusts responses based on detected user emotions.
  • Context-Aware Conversations β†’ Remembers past interactions for coherent discussions.
  • Journal Mood Pattern Analysis β†’ Tracks mood trends over time.
  • Moderation & Toxicity Filtering β†’ Ensures safe and ethical interactions.
  • Emergency Contact Redirection β†’ Provides immediate help when distress signals are detected.
  • Optimized Model Performance β†’ Uses LoRA and 4-bit quantization for efficiency.
  • Hosted on RTX 4090 β†’ Faster checkpoint downloads and improved inference speed.

Model Training Details

  • Base Model β†’ Fine-tuned LLaMA-2 for mental health counseling.
  • Training Framework β†’ PyTorch, Hugging Face Transformers.
  • Optimization Techniques β†’ LoRA, 4-bit quantization.
  • Dataset Used β†’ Custom dataset of mental health counseling conversations.
  • Training Environment β†’ Google Colab with GPU support & RTX 4090 desktop for inference acceleration.

How to Run on Google Colab

  • Open Google Colab: Go to Google Colab

    • Upload the Notebook:
    • Click on File β†’ Upload Notebook
    • Select GoatedModel_MHB.ipynb from your local storage. (It can be downloaded from the 'Files and Versions' tab of our Hugging Face repo.)
  • Enable GPU:

    • Click on Runtime β†’ Change runtime type
    • Set Hardware accelerator to GPU.
  • Run the Notebook:

    • Execute all cells sequentially.
    • The model will be downloaded, set up, and ready for interaction.

Usage

  • The chatbot runs interactively in the Colab notebook.
  • Users can enter queries, and the model will generate responses accordingly.
  • Outputs can be analyzed for emotional insights and response quality.

Dependencies

  • The notebook automatically installs required dependencies, but ensure the following packages are installed if needed:
  • !pip install torch transformers unsloth langchain llama-index

Future Enhancements

  • Adding voice-based interactions.
  • Integrating mindfulness and relaxation exercises.
  • AI-powered therapy mode selection (CBT, mindfulness, etc.).

Notes

  • This chatbot is not a substitute for professional mental health support.
  • Ensure ethical usage and refrain from using the bot for harmful purposes.

Repository Links

Acknowledgments

  • Built with Hugging Face Transformers and PyTorch.
  • Developed by Siddharth Amdal/Swapnil Patidar with optimization for efficient AI-based counseling.

For any issues or contributions, feel free to open a pull request or contact us!

Downloads last month
-
Safetensors
Model size
7B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support