Skip to content

Llama-2's Mental Therapy Chatbot: fine-tuned 7B & 13B models for empathetic conversations. Made using HF Transformers, Gradio UI and deployed using HF TGI-Inference, FastAPI and Docker

License

Notifications You must be signed in to change notification settings

vibhorag101/phr-mental-chat

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

68 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

phr-mental-chat

A mental therapy chatbot

Model and dataset details:

  • The original dataset is accessible at here
  • The modified dataset for llama-2 format is accessible at here
  • The finetuned llama-2-7b-chat-hf model is accessible at here

To build the docker image, run following commands:

docker build -t {image_name} .
docker run --gpus all -p 5555:5555  -itd --name {container_name} {image_name}
  • Chatbot will be accessible at http://{server_ip}:5555/gradio
  • Chatbot API will be accessible at http://{server_ip}:5555/generate
  • Roberta Emotion Classification api will be accessible at http://{server_ip}:5555/emotion
  • Suicide Prediction api will be accessible at http://{server_ip}:5555/suicide
  • Plutchik Emotion API available at http://{server_ip}:5000/predict_sentiment and http://{server_ip}:5000/predict_sentiment_scores
  • The API docs are available at http://{server_ip}:5555/docs

About

Llama-2's Mental Therapy Chatbot: fine-tuned 7B & 13B models for empathetic conversations. Made using HF Transformers, Gradio UI and deployed using HF TGI-Inference, FastAPI and Docker

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published