This project implements a DeepSeek LLM-based sentiment analysis application using Streamlit for an interactive web interface. The model, deepseek-ai/deepseek-llm-7b-base, is loaded with transformers and deployed via Google Colab. The app accepts text input from users and analyzes sentiment by generating a response from the model, returning only one of three possible outputs: POSITIVE, NEGATIVE, or NEUTRAL. The pipeline is optimized for automatic device selection (device_map="auto") and utilizes offloading to manage memory efficiently. Streamlit serves the app on port 8501, and a Colab proxy exposes it via a public URL.
Category tags:An AI-driven tool that reviews GitHub pull requests in real-time, providing clear and intelligent code feedback using Groq-accelerated LLaMA models and the BLACKBOX.AI Coding Agent.
innoventors-blackbox-track
Flowrish AI helps students think better, not less. It guides reflection instead of giving answers—strengthening minds, not replacing them. Offline-first on Snapdragon X Elite, with LLaMA 3 locally and Groq online. Because learning should grow you.
42AI Qualcomm Track
Amagi is a proactive AI assistant that sees your screen, listens, remembers, and helps you stay focused—designed to run across devices with real-time context awareness
The Monad (AI-Smith Protocol) -Vultr Track
An AI-powered shopping assistant built with FastAPI, Groq API (LLaMA models), and Neo4j knowledge graph for personalized e-commerce experiences
Hackcelerate - Prosus Track
A privacy-focused toolkit for real-time screen OCR and audio transcription on any PC, combining universal image text extraction, audio-to-text, and fast local semantic search—powered by Edge AI and Groq API.
Illuminative Lab - Qualcomm Track
An AI-driven tool that reviews GitHub pull requests in real-time, providing clear and intelligent code feedback using Groq-accelerated LLaMA models and the BLACKBOX.AI Coding Agent.
innoventors-blackbox-track
Flowrish AI helps students think better, not less. It guides reflection instead of giving answers—strengthening minds, not replacing them. Offline-first on Snapdragon X Elite, with LLaMA 3 locally and Groq online. Because learning should grow you.
42AI Qualcomm Track
Amagi is a proactive AI assistant that sees your screen, listens, remembers, and helps you stay focused—designed to run across devices with real-time context awareness
The Monad (AI-Smith Protocol) -Vultr Track
An AI-powered shopping assistant built with FastAPI, Groq API (LLaMA models), and Neo4j knowledge graph for personalized e-commerce experiences
Hackcelerate - Prosus Track
A privacy-focused toolkit for real-time screen OCR and audio transcription on any PC, combining universal image text extraction, audio-to-text, and fast local semantic search—powered by Edge AI and Groq API.
Illuminative Lab - Qualcomm Track