[docs] fix: Address model docs review comments

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

Author: yaoyu-33

README.md

@@ -39,7 +39,6 @@ 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

docs/index.md

@@ -13,8 +13,7 @@ Megatron Bridge conversion, training recipe links, and model-specific notes.
 | **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) |
+| **Mistral** | [Mistral](mistral/mistral.md), [Ministral 3](mistral/ministral3.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) |
@@ -59,6 +58,7 @@ Each model documentation page typically includes:
 
 - Gemma 3 VL and Gemma 4 VL
 - GLM-4.5V
+- Ministral 3
 - Nemotron Nano V2 VL and Nemotron-3 Nano Omni
 - Qwen2.5-VL, Qwen3-VL, Qwen3.5 / 3.6, and Qwen3-Omni
 

docs/models/README.md

@@ -1,13 +1,15 @@
 # Mistral
 
-Mistral model documentation is organized by model variant.
+Mistral model documentation is organized by model variant, including Ministral.
 
 ```{toctree}
 :hidden:
 
 mistral.md
+ministral3.md
 ```
 
 | Variant | Guide |
 |---------|-------|
 | Mistral | [mistral.md](mistral.md) |
+| Ministral 3 | [ministral3.md](ministral3.md) |

docs/models/ministral/index.md

@@ -1,10 +1,10 @@
 # Ministral 3
 
-[Mistral AI's Ministral 3](https://huggingface.co/collections/mistralai/ministral-3) is a family of edge-optimized vision-language models designed for deployment across various hardware configurations. The Ministral 3 architecture combines a powerful language model with a vision encoder for multimodal understanding.
+[Mistral AI's Ministral 3](https://huggingface.co/collections/mistralai/ministral-3) is part of the Mistral family and is designed for edge-optimized vision-language deployment across various hardware configurations. The Ministral 3 architecture combines a powerful language model with a vision encoder for multimodal understanding.
 
 Ministral 3 models support multimodal tasks including image captioning, visual question answering, OCR, and general vision-language understanding. Despite their compact size, these models deliver strong performance for on-device and edge deployment scenarios.
 
-Ministral family models are supported via the Bridge system with auto-detected configuration and weight mapping.
+Ministral 3 models are supported via the Bridge system with auto-detected configuration and weight mapping.
 
 ```{important}
 Please upgrade to `transformers` v5 and upgrade `mistral-common` in order to use the Ministral 3 models.
@@ -51,7 +51,7 @@ Ministral 3 combines efficient language modeling with multimodal capabilities:
 
 ## Examples
 
-For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [Ministral 3 Examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/ministral/ministral3/README.md).
+For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [Ministral 3 examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/ministral/ministral3/README.md).
 
 ## Hugging Face Model Cards
 
@@ -63,7 +63,7 @@ For checkpoint conversion, inference, finetuning recipes, and step-by-step train
 - Ministral 3 14B Instruct: https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512
 
 ## Related Docs
-- Related Mistral variant: [Mistral](../mistral/mistral.md)
+- Related Mistral variant: [Mistral](mistral.md)
 - Recipe usage: [Recipe usage](../../recipe-usage.md)
 - Customizing the training recipe configuration: [Configuration overview](../../training/config-container-overview.md)
 - Training entry points: [Entry points](../../training/entry-points.md)

docs/models/mistral/index.md

@@ -97,7 +97,7 @@ Training recipes for Mistral models are not currently available. The Bridge supp
 - Mistral Documentation: https://docs.mistral.ai/
 
 ## Related Docs
+- Related Mistral variant: [Ministral 3](ministral3.md)
 - Recipe usage: [Recipe usage](../../recipe-usage.md)
 - Customizing the training recipe configuration: [Configuration overview](../../training/config-container-overview.md)
 - Training entry points: [Entry points](../../training/entry-points.md)
-

docs/models/ministral/ministral3.md docs/models/mistral/ministral3.mddocs/models/ministral/ministral3.md renamed to docs/models/mistral/ministral3.md

@@ -2,7 +2,7 @@
 
 This directory contains example scripts for Ministral 3 vision-language models.
 
-For model introduction and architecture details, see the [Ministral 3 documentation](../../../../docs/models/ministral/ministral3.md).
+For model introduction and architecture details, see the [Ministral 3 documentation](../../../../docs/models/mistral/ministral3.md).
 
 ## Workspace Configuration