index.md

Nemotron Training Recipes

Open and efficient models for agentic AI — reproducible training pipelines with fully transparent data, techniques, and weights.

<iframe width="560" height="315" src="https://www.youtube.com/embed/_y9SEtn1lU8" title="Nemotron Overview" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>

Quick Start

// Install the Nemotron training recipes
$ git clone https://github.com/NVIDIA/nemotron
$ cd nemotron && uv sync

// Run the full Nano3 pipeline
$ uv run nemotron nano3 data prep pretrain --run YOUR-CLUSTER
$ uv run nemotron nano3 pretrain --run YOUR-CLUSTER
$ uv run nemotron nano3 data prep sft --run YOUR-CLUSTER
$ uv run nemotron nano3 sft --run YOUR-CLUSTER
$ uv run nemotron nano3 data prep rl --run YOUR-CLUSTER
$ uv run nemotron nano3 rl --run YOUR-CLUSTER

Note: The --run YOUR-CLUSTER flag submits jobs to your configured Slurm cluster via NeMo-Run. See Execution through NeMo-Run for setup instructions.

Usage Cookbook & Examples

::::{grid} 1 2 2 2 :gutter: 3

:::{grid-item-card} Usage Cookbook :link: usage-cookbook/README :link-type: doc

Deployment guides for Nemotron models: TensorRT-LLM, vLLM, SGLang, NIM, and Hugging Face. :::

:::{grid-item-card} Use Case Examples :link: use-case-examples/README :link-type: doc

End-to-end applications: RAG agents, ML agents, and multi-agent systems. :::

::::

Available Training Recipes

::::{grid} 1 2 2 2 :gutter: 3

:::{grid-item-card} Nemotron 3 Nano :link: train/nano3/README :link-type: doc

31.6B total / 3.6B active parameters, 25T tokens, up to 1M context. Hybrid Mamba-Transformer with sparse MoE.

Stages: Pretraining → SFT → RL :::

::::

Training Pipeline

The Nemotron training pipeline follows a four-stage approach with full artifact lineage tracking:

Stage	Name	Description
0	Pretraining	Base model training on large text corpus
1	SFT	Supervised fine-tuning for instruction following
2	RL	Reinforcement learning for alignment
3	Evaluation	Benchmark testing with NeMo Evaluator

Why Nemotron?

Open Models	Transparent training data, techniques, and weights for community innovation
Compute Efficiency	Model pruning enabling higher throughput via TensorRT-LLM
High Accuracy	Built on frontier open models with human-aligned reasoning
Flexible Deployment	Deploy anywhere — edge, single GPU, or data center with NIM

Key Features

• Complete Pipelines — From raw data to deployment-ready models
• Artifact Lineage — Full traceability via W&B from data to model
• Production-Grade — Built on NVIDIA's NeMo stack (Megatron-Bridge, NeMo-RL)
• Reproducible — Versioned configs, data blends, and checkpoints

Resources

• Tech Report — Nemotron 3 Nano methodology
• Model Weights — Pre-trained checkpoints on HuggingFace
• Pre-training Datasets — Open pre-training data
• Post-training Datasets — SFT and RL data
• Artifact Lineage — W&B integration guide

:caption: Usage Cookbook
:hidden:

usage-cookbook/README.md
usage-cookbook/Nemotron-Nano2-VL/README.md
usage-cookbook/Nemotron-Parse-v1.1/README.md

:caption: Use Case Examples
:hidden:

use-case-examples/README.md
use-case-examples/Simple Nemotron-3-Nano Usage Example/README.md
use-case-examples/Data Science ML Agent/README.md
use-case-examples/RAG Agent with Nemotron RAG Models/README.md

:caption: Training Recipes
:hidden:

train/nano3/README.md
train/artifacts.md

:caption: Nano3 Stages
:hidden:

train/nano3/pretrain.md
train/nano3/sft.md
train/nano3/rl.md
train/nano3/eval.md
train/nano3/import.md

:caption: Nemotron Kit
:hidden:

train/kit.md
train/nvidia-stack.md
train/nemo-run.md
train/omegaconf.md
train/wandb.md
train/cli.md
train/data-prep.md
train/evaluator.md