NVIDIA

This is an NVIDIA AI Workbench example project that demonstrates an end-to-end model development workflow using Llamafactory.

Scalable toolkit for data curation

An NVIDIA AI Workbench example project for customizing an SDXL model

An NVIDIA AI Workbench Example Project for Finetuning Llama 2

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Accelerate your Generative AI with NIMs.

Transformer related optimization, including BERT, GPT

Ongoing research training transformer models at scale