Публичный след на GitHub NVIDIA-NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

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

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

Scalable toolkit for efficient model reinforcement

Scalable data pre processing and curation toolkit for LLMs

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

Evaluate and improve models and agents using environments

A project to improve skills of large language models

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Agentic RL on Any Harness at Scale

Open-source library for scalable, reproducible evaluation of AI models and benchmarks.

A tool to configure, launch and manage your machine learning experiments.

Описание для этого репозитория не предоставлено.

🕵️ NeMo Anonymizer: Detect and protect PII through context-aware replacement and rewriting

State-of-the-art framework for fast, large-scale training and inference of diffusion models

Make the agents you ship faster, more accurate, and safer.

A library for exporting models including NeMo and Hugging Face to optimized inference backends, and deploying them for efficient querying

:shield: NeMo Safe Synthesizer: Create private, safe versions of sensitive tabular datasets.

CI/CD templates for NeMo-FW libraries

🔌 🎨 NeMo Data Designer Plugins

NeMo SDG-PGMs is a user-friendly Python library for building probabilistic graphical models (PGMs) to generate synthetic data

Описание для этого репозитория не предоставлено.