Large Language Models

This directory contains documentation for Large Language Models (LLMs) supported by Megatron Bridge. Each model documentation includes examples for converting to/from 🤗 Hugging Face and links to training recipes.

Available Models

Megatron Bridge supports the following LLM families:

Model	Documentation	Description
DeepSeek V2	deepseek-v2.md	DeepSeek V2 model family
DeepSeek V3	deepseek-v3.md	DeepSeek V3 model family
Gemma 2	gemma2.md	Google Gemma 2 models
Gemma 3	gemma3.md	Google Gemma 3 models
GLM-4.5	glm45.md	GLM-4.5 model family
GPT-OSS	gpt-oss.md	Open-source GPT-style models
LLaMA 3	llama3.md	Meta LLaMA 3 models
LLaMA Nemotron	llama-nemotron.md	NVIDIA LLaMA Nemotron models
Mistral	mistral.md	Mistral AI models
Moonlight	moonlight.md	Moonlight model family
Nemotron-3	nemotron3.md	NVIDIA Nemotron-3 models
Nemotron-H	nemotronh.md	NVIDIA Nemotron-H models
OLMoE	olmoe.md	OLMoE (Open Language Model - Mixture of Experts)
Qwen	qwen.md	Alibaba Cloud Qwen model family

Quick Navigation

I want to

🔍 Find a specific model → Browse the model list above or use the index page

🔄 Convert models between formats → Each model page includes conversion examples for Hugging Face ↔ Megatron Bridge

🚀 Get started with training → See Training Documentation for training guides

📚 Understand model architecture → Each model page documents architecture-specific features and configurations

🔧 Add support for a new model → Refer to Adding New Models

Related Documentation

• Models Overview - Return to main models documentation

• Vision Language Models - VLM model documentation

• Training Documentation - Training and customization guides

• Bridge Guide - Working with Hugging Face models

• Adding New Models - Extending model support

Model Documentation Structure

Each model documentation page typically includes:

1. Model Overview - Architecture and key features

2. Available Variants - Supported model sizes and configurations

3. Conversion Examples - Converting between Hugging Face and Megatron formats

4. Training Recipes - Links to training configurations and examples

5. Architecture Details - Model-specific features and configurations

---

Ready to explore? Choose a model from the list above or return to the main documentation.