basim123/fastapi repository overview

To run this app kindly use this command: docker run --gpus all -p 8060:8060 basim123/fastapi:latest

This app consists of a simple HTML, CSS and JavaScript based frontend connected to a API using flask running a quantized gptq based Llama-2 7b model (6GB) vram must required.

This is a test for NLM engineer at OuterAspect IP Ltd position to create a chatbot system from scratch and host using docker.

Application can be accessed at: http://127.0.0.1:8086⁠

Candidiate: Shoaib Ahmed