--- title: braingpt_implement emoji: πŸ¦€ colorFrom: gray colorTo: blue sdk: docker pinned: false short_description: Implementing braingpt using BrainGPT-7B-v0.1 --- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference This app currently uses **BrainGPT** as the model engine for generating and evaluating abstracts. --- ## πŸš€ Features - πŸ§ͺ Presents users with neuroscience abstracts (either original or altered). - βœ… Users decide if an abstract is AI-modified and rate their confidence. - πŸ€– BrainGPT model evaluates the same abstract. - πŸ“Š Results compare user guesses vs model output in a clear, styled interface. - πŸ“‚ Backed by a curated dataset hosted on Hugging Face Datasets. - πŸ› οΈ Fully Dockerized FastAPI application deployed via Hugging Face Spaces. --- ## πŸ“¦ Tech Stack - **Frontend**: Jinja2 + Tailwind-style CSS - **Backend**: FastAPI - **Model**: `BrainGPT-7B-v0.1` via Hugging Face Transformers - **Hosting**: Hugging Face Spaces (Docker SDK) - **Dataset**: Custom neuroscience benchmark (Parquet format) --- ## πŸ”§ Endpoints - `/`: Home page - `/start`: Begin a new session (random abstract trials) - `/trial`: Active abstract assessment - `/submit-trial`: Submit a response, compare with model - `/results`: View summary of performance - `/predict`: POST endpoint used internally to get BrainGPT-7B-v0.1 output --- ## 🧠 Example Use Case 1. A neuroscience researcher lands on the app. 2. They read an abstract and guess whether it’s been altered. 3. They rate their confidence. 4. BrainGPT-7B-v0.1 also analyzes the abstract. 5. After 3 rounds, the app displays a comparison: who got what right? --- ## πŸ“Œ Current Model - Model: [`BrainGPT-7B-v0.1`](https://huggingface.co/BrainGPT/BrainGPT-7B-v0.1) - Reason: Fast, lightweight, deployable in CPU-only Spaces --- ## πŸ—ΊοΈ Roadmap - [ ] Add leaderboard tracking - [ ] Expand dataset with more domains --- ## πŸ™Œ Credits Built by **Dr. David Andai** β€” a general practitioner & data scientist passionate about mental health and AI.