top of page
Allan Visochek Portfolio
Create Your First Project
Start adding your projects to your portfolio. Click on "Manage Projects" to get started
Simple Chatbot
A simple chatbot implementing the open source mistral-instruct LLM. This was an exercise in understanding the hardware and technical requirements in order to run and fully host an LLM.
Hosting: Lambda Cloud
GPU: Nvidia RTX A6000
Model: Mistral-Instruct-2
LLM Execution: Hugging Face AutoTransformerFromLLM Library (a wrapper around Tensor Flow, Pytorch, Cuda and others)
Backend: Nginx and Streamlit
Frontend: Streamlit
bottom of page