README.md

metadata

title: DenisCare
emoji: 💬
developed_by: Dynamo Denis Mbugua
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.42.0
app_file: app.py
pinned: false
hf_oauth: true
hf_oauth_scopes:
  - inference-api
short_description: Fine tuned model from llama2 trained to offer medical help

Description

Developed and Trained by Denis Mbugua Wanjiru dynamodenis254

This model is fine tuned from llama2 model which has over 7 billion parameters. Since thats too big of information we fine tune it to only focus on medical search terms which I got the data set from aboonaji/wiki_medical_terms_llam2_format. It might be slow since I'm using free CPU for demo purpose and I don't really want to get a pro subscription for this project since its just for demo purpose. When I used Upgraded GPU the answer was in seconds . I also tested on Google Colab since it use it for training and development and it has a free T4 GPU.

An example chatbot using Gradio, huggingface_hub, and the Hugging Face Inference API.