[docs] refactor: Organize model docs by brand

Signed-off-by: yaoyu-33 <yaoyu.094@gmail.com>

Author: yaoyu-33

README.md

@@ -1,6 +1,6 @@
 # Megatron Bridge Documentation
 
-Welcome to the Megatron Bridge documentation! This guide helps you navigate our comprehensive documentation to find exactly what you need for training, converting, and working with large language models and vision language models.
+Welcome to the Megatron Bridge documentation! This guide helps you navigate our comprehensive documentation to find exactly what you need for training, converting, and working with language, vision-language, audio, and multimodal models.
 
 ## 🚀 Quick Start Paths
 
@@ -16,7 +16,7 @@ Welcome to the Megatron Bridge documentation! This guide helps you navigate our
 → See [Training Documentation](training/README.md) for comprehensive training guides
 
 **📚 Find model documentation**
-→ Browse [Supported Models](models/llm/index.md) for LLMs or [Vision Language Models](models/vlm/index.md) for VLMs
+→ Browse [Supported Models](models/README.md), organized by brand and model variant
 
 **🔧 Migrate from NeMo 2 or Megatron-LM**
 → Check [NeMo 2 Migration Guide](nemo2-migration-guide.md) or [Megatron-LM Migration Guide](megatron-lm-to-megatron-bridge.md)
@@ -38,7 +38,7 @@ Welcome to the Megatron Bridge documentation! This guide helps you navigate our
 
 - **Start here:** [Bridge Guide](bridge-guide.md) → [Training Documentation](training/README.md)
 - **Deep dive:** [Performance Guide](performance-guide.md) → [Training Optimization Guides](training/README.md#optimization-and-performance)
-- **Model support:** [Supported Models](models/llm/index.md) → [Adding New Models](adding-new-models.md)
+- **Model support:** [Supported Models](models/README.md) → [Adding New Models](adding-new-models.md)
 
 ### For Training Engineers
 
@@ -49,7 +49,7 @@ Welcome to the Megatron Bridge documentation! This guide helps you navigate our
 ### For Model Developers
 
 - **Start here:** [Bridge Guide](bridge-guide.md) → [Bridge Tech Details](bridge-tech-details.md)
-- **Model support:** [Adding New Models](adding-new-models.md) → [Model Documentation](models/llm/index.md)
+- **Model support:** [Adding New Models](adding-new-models.md) → [Model Documentation](models/README.md)
 - **Integration:** [Bridge RL Integration](bridge-rl-integration.md)
 
 ### For DevOps & Platform Teams
@@ -76,8 +76,7 @@ Welcome to the Megatron Bridge documentation! This guide helps you navigate our
 
 | Document | Purpose | When to Read |
 |----------|---------|--------------|
-| **[Large Language Models](models/llm/index.md)** | LLM model documentation | Working with LLM models |
-| **[Vision Language Models](models/vlm/index.md)** | VLM model documentation | Working with VLM models |
+| **[Supported Models](models/README.md)** | Brand-organized model documentation | Working with supported model variants |
 | **[Adding New Models](adding-new-models.md)** | Guide for adding model support | Extending model support |
 
 ### Training and Customization
@@ -149,7 +148,7 @@ Welcome to the Megatron Bridge documentation! This guide helps you navigate our
 
 1. [Bridge Guide](bridge-guide.md) *(conversion basics)*
 2. [Bridge Tech Details](bridge-tech-details.md) *(technical details)*
-3. [Supported Models](models/llm/index.md) or [Vision Language Models](models/vlm/index.md) *(model-specific guides)*
+3. [Supported Models](models/README.md) *(model-specific guides)*
 4. [Adding New Models](adding-new-models.md) *(extend support)*
 
 ### 🔧 Customization and Extension
@@ -186,12 +185,9 @@ Welcome to the Megatron Bridge documentation! This guide helps you navigate our
 
 #### [models/](models/README.md)
 
-- **[llm/](models/llm/README.md)** - Large Language Model documentation
-  - Individual model guides (Qwen, LLaMA, Mistral, etc.)
-  - Conversion examples and training recipes
-- **[vlm/](models/vlm/README.md)** - Vision Language Model documentation
-  - VLM model guides (Qwen VL, Gemma VL, etc.)
-  - Multimodal model support
+- Brand folders such as **[qwen/](models/qwen/index.md)**, **[gemma/](models/gemma/index.md)**, and **[nemotron/](models/nemotron/index.md)**
+  - Model-variant guides for conversion, training recipes, and architecture notes
+  - Multimodal variants live with their brand families
 
 #### [training/](training/README.md)
 
@@ -239,8 +235,8 @@ graph TD
     I --> N[Data Parallelism<br/>DDP]
     I --> O[Model Parallelism<br/>TP/PP/VPP]
     
-    D --> P[LLM Models<br/>Language Models]
-    D --> Q[VLM Models<br/>Vision Language Models]
+    D --> P[Brand Index<br/>Model Variants]
+    D --> Q[Model Pages<br/>Recipes and Conversion]
     
     style A fill:#e1f5fe
     style B fill:#f3e5f5

docs/README.md

@@ -33,8 +33,18 @@ bridge-tech-details.md
 :caption: Supported Models
 :hidden:
 
-models/llm/index.md
-models/vlm/index.md
+models/README.md
+models/deepseek/index.md
+models/gemma/index.md
+models/glm/index.md
+models/gpt_oss/index.md
+models/llama/index.md
+models/ministral/index.md
+models/mistral/index.md
+models/moonlight/index.md
+models/nemotron/index.md
+models/olmoe/index.md
+models/qwen/index.md
 ```
 
 ```{toctree}
@@ -106,9 +116,6 @@ skills-index
 :hidden:
 
 README.md
-models/README.md
-models/llm/README.md
-models/vlm/README.md
 releases/README.md
 training/README.md
 modelopt/README.md

docs/index.md

@@ -1,75 +1,42 @@
 # Supported Models
 
-This directory contains documentation for all models supported by Megatron Bridge, including Large Language Models (LLMs) and Vision Language Models (VLMs). Each model documentation includes architecture details, conversion examples for Hugging Face ↔ Megatron Bridge, and links to training recipes.
-
-## Model Categories
-
-Megatron Bridge supports two main categories of models:
-
-### 🔤 Large Language Models (LLMs)
-
-Text-only models for language understanding and generation tasks.
-
-| Category | Model Count | Documentation |
-|----------|-------------|---------------|
-| **Large Language Models** | 13 models | [LLM Documentation](llm/README.md) |
-
-**Supported LLM Families:**
-
-- DeepSeek (V2, V3)
-- Gemma (2, 3)
-- GLM-4.5
-- GPT-OSS
-- LLaMA (3, Nemotron)
-- Mistral
-- Moonlight
-- Nemotron-H
-- OLMoE
-- Qwen (2, 2.5, 3, 3 MoE, 3-Next)
-
-### 🖼️ Vision Language Models (VLMs)
-
-Multimodal models that combine vision and language capabilities.
-
-| Category | Model Count | Documentation |
-|----------|-------------|---------------|
-| **Vision Language Models** | 5 models | [VLM Documentation](vlm/README.md) |
-
-**Supported VLM Families:**
-
-- Gemma 3 VL
-- Nemotron-3 Nano Omni (image + video + audio + text)
-- Nemotron Nano V2 VL
-- Qwen (2.5 VL, 3 VL)
-
----
+This directory contains brand-organized documentation for models supported by
+Megatron Bridge. Each model page covers supported variants, Hugging Face <->
+Megatron Bridge conversion, training recipe links, and model-specific notes.
+
+## Brand Index
+
+| Brand / family | Model documentation |
+|----------------|---------------------|
+| **DeepSeek** | [DeepSeek V2](deepseek/deepseek-v2.md), [DeepSeek V3](deepseek/deepseek-v3.md), [DeepSeek V4](deepseek/deepseek-v4.md) |
+| **Gemma** | [Gemma 2](gemma/gemma2.md), [Gemma 3](gemma/gemma3.md), [Gemma 3 VL](gemma/gemma3-vl.md), [Gemma 4 VL](gemma/gemma4-vl.md) |
+| **GLM** | [GLM 4.5](glm/glm45.md), [GLM-4.5V](glm/glm-45v.md) |
+| **GPT-OSS** | [GPT OSS](gpt_oss/gpt-oss.md) |
+| **Llama** | [Llama 3](llama/llama3.md) |
+| **Ministral** | [Ministral 3](ministral/ministral3.md) |
+| **Mistral** | [Mistral](mistral/mistral.md) |
+| **Moonlight** | [Moonlight](moonlight/moonlight.md) |
+| **Nemotron** | [Llama Nemotron](nemotron/llama-nemotron.md), [Nemotron H and Nemotron Nano v2](nemotron/nemotronh.md), [Nemotron-3 Nano](nemotron/nemotron3-nano.md), [Nemotron-3 Super](nemotron/nemotron3-super.md), [Nemotron Nano V2 VL](nemotron/nemotron-nano-v2-vl.md), [Nemotron-3 Nano Omni](nemotron/nemotron-3-omni.md) |
+| **OLMoE** | [OLMoE](olmoe/olmoe.md) |
+| **Qwen** | [Qwen](qwen/qwen.md), [Qwen2.5-VL](qwen/qwen2.5-vl.md), [Qwen3-VL](qwen/qwen3-vl.md), [Qwen3.5 / 3.6](qwen/qwen35-vl.md), [Qwen3-Omni](qwen/qwen3-omni.md) |
 
 ## Quick Navigation
 
 ### I want to
 
-**🔍 Find a specific LLM model**
-→ Browse [Large Language Models](llm/README.md) documentation
-
-**🖼️ Find a specific VLM model**
-→ Browse [Vision Language Models](vlm/README.md) documentation
-
-**🔄 Convert models between formats**
-→ See [Bridge Guide](../bridge-guide.md) for Hugging Face ↔ Megatron conversion
-
-**🚀 Get started with training**
-→ See [Training Documentation](../training/README.md) for training guides
+**Find model-specific docs**
+-> Browse the brand index above or use the navigation for the model's brand.
 
-**📚 Understand model architectures**
-→ Each model page documents architecture-specific features and configurations
+**Convert models between formats**
+-> See [Bridge Guide](../bridge-guide.md) for Hugging Face <-> Megatron
+conversion basics. Model pages include model-specific commands where available.
 
-**🔧 Add support for a new model**
-→ Refer to [Adding New Models](../adding-new-models.md)
+**Get started with training**
+-> See [Training Documentation](../training/README.md) for training guides and
+[Recipe Usage](../recipe-usage.md) for pre-configured training recipes.
 
-**📊 Use training recipes**
-→ Read [Recipe Usage](../recipe-usage.md) for pre-configured training recipes
-
----
+**Add support for a new model**
+-> Refer to [Adding New Models](../adding-new-models.md).
 
 ## Model Documentation Structure
 
@@ -81,147 +48,35 @@ Each model documentation page typically includes:
 4. **Training Recipes** - Links to training configurations and examples
 5. **Architecture Details** - Model-specific features and configurations
 
----
-
-## Common Tasks by Model Type
-
-### For LLM Models
-
-**Training:**
-
-- Pretraining on large corpora
-- Supervised fine-tuning (SFT)
-- Parameter-efficient fine-tuning (PEFT/LoRA)
-- Preference optimization (DPO)
-
-**Deployment:**
-
-- Export to Hugging Face format
-- Integration with inference engines
-- Model serving and deployment
-
-**Use Cases:**
-
-- Text generation
-- Question answering
-- Conversational AI
-- Code generation
-
-### For VLM Models
-
-**Training:**
-
-- Multimodal pretraining
-- Vision-language alignment
-- Fine-tuning on visual tasks
-
-**Deployment:**
+## Model Support Overview
 
-- Export to Hugging Face format
-- Multimodal inference
+### Decoder-Only and Hybrid Backbones
 
-**Use Cases:**
+- DeepSeek, Gemma, GLM, GPT-OSS, Llama, Mistral, Moonlight, Nemotron, OLMoE, and Qwen
+- MoE and hybrid variants including DeepSeek, GLM, GPT-OSS, Nemotron-3, OLMoE, Qwen3-MoE, and Qwen3-Next
 
-- Image captioning
-- Visual question answering
-- Document understanding
-- Multimodal reasoning
+### Multimodal Variants
 
----
+- Gemma 3 VL and Gemma 4 VL
+- GLM-4.5V
+- Nemotron Nano V2 VL and Nemotron-3 Nano Omni
+- Qwen2.5-VL, Qwen3-VL, Qwen3.5 / 3.6, and Qwen3-Omni
 
 ## Related Documentation
 
-### Getting Started
-
 - **[Main Documentation](../README.md)** - Return to main documentation
-- **[Bridge Guide](../bridge-guide.md)** - Hugging Face ↔ Megatron conversion
+- **[Bridge Guide](../bridge-guide.md)** - Hugging Face <-> Megatron conversion
 - **[Bridge Tech Details](../bridge-tech-details.md)** - Technical details of the bridge system
-
-### Training Resources
-
 - **[Training Documentation](../training/README.md)** - Comprehensive training guides
-- **[Configuration Container](../training/config-container-overview.md)** - Training configuration
-- **[Parallelisms Guide](../parallelisms.md)** - Data and model parallelism strategies
-- **[Performance Guide](../performance-guide.md)** - Performance optimization
-
-### Advanced Topics
-
 - **[Adding New Models](../adding-new-models.md)** - Extending model support
 - **[Recipe Usage](../recipe-usage.md)** - Using pre-configured training recipes
-- **[Bridge RL Integration](../bridge-rl-integration.md)** - Reinforcement learning integration
-- **[PEFT](../training/peft.md)** - Parameter-efficient fine-tuning
-
----
-
-## Model Support Overview
-
-### By Architecture Type
-
-**Decoder-Only (Autoregressive):**
-
-- GPT-style models (GPT-OSS)
-- LLaMA family (LLaMA 3, LLaMA Nemotron)
-- Qwen family (Qwen 2, 2.5, 3, 3-Next)
-- Gemma family (Gemma 2, 3)
-- DeepSeek family (DeepSeek V2, V3)
-- Mistral, Moonlight, Nemotron-H, GLM-4.5
-
-**Mixture-of-Experts (MoE):**
-
-- Qwen 3 MoE, Qwen 3-Next
-- DeepSeek V2, V3
-- OLMoE
-
-**Vision-Language (Multimodal):**
-
-- Gemma 3 VL
-- Qwen 2.5 VL, Qwen 3 VL
-- Nemotron Nano V2 VL
-- Nemotron-3 Nano Omni
-
-### By Provider
-
-**Meta/LLaMA:**
-
-- LLaMA 3
-
-**NVIDIA:**
-
-- LLaMA Nemotron
-- Nemotron-H
-- Nemotron Nano V2 VL
-- Nemotron-3 Nano Omni
-
-**Alibaba Cloud:**
-
-- Qwen (2, 2.5, 3, 3 MoE, 3-Next)
-- Qwen VL (2.5, 3)
-
-**Google:**
-
-- Gemma (2, 3)
-- Gemma 3 VL
-
-**DeepSeek:**
-
-- DeepSeek (V2, V3)
-
-**Other:**
-
-- Mistral AI (Mistral)
-- GLM-4.5
-- GPT-OSS
-- Moonlight
-- OLMoE
-
----
 
 ## Conversion Support
 
-All models support bidirectional conversion:
+All model pages document support for one or both conversion directions:
 
-- **Hugging Face → Megatron Bridge**: Load pretrained weights for training
-- **Megatron Bridge → Hugging Face**: Export trained models for deployment
+- **Hugging Face -> Megatron Bridge**: Load pretrained weights for training
+- **Megatron Bridge -> Hugging Face**: Export trained models for deployment
 
 Conversion features:
 
@@ -231,12 +86,3 @@ Conversion features:
 - Verification mechanisms for conversion accuracy
 
 Refer to the [Bridge Guide](../bridge-guide.md) for detailed conversion instructions.
-
----
-
-**Ready to explore?** Choose a model category:
-
-- [Large Language Models (LLMs)](llm/README.md)
-- [Vision Language Models (VLMs)](vlm/README.md)
-
-Or return to the [main documentation](../README.md).