A lightweight LLaMA.cpp HTTP server image based on Alpine.

Containerized models, tested and ready for production, focused on smaller LLMs.

docker run -d -p 11434:11434 --name mistral yashbhesaniya/ollama_mistral

Apache-based web user interface for the Data Llama Augmented Data Catalog.

Image size: ~2.85MiB. Llama GPT, written in go. USER: nobody.

Neural Binary Classification Example using CNTK Python Libraries

Containerized models served with llama optimized for 6GB VRAM NVidia GPUs using CUDA

Adds AI model support to Hyperglance