Make model_index the public entry

README.md

@@ -190,14 +190,14 @@ Each checkpoint is distributed as a self\-contained Hugging Face\-style reposito
 
 Download the model. The repository hosts the original checkpoint (`FL2VA/`, `Ref2VA/`) and the diffusers format side by side, so scope the download to what your framework needs:
 
-`model_index.json` is the repository-level modular index. The task-family-specific diffusers indexes remain under `FL2VA/model_index.json` and `Ref2VA/model_index.json`.
+`model_index.json` is the repository-level public entry. The task-family-specific diffusers indexes remain under `FL2VA/model_index.json` and `Ref2VA/model_index.json`.
 
 ```bash
 # Original checkpoint, both task families (SGLang, vLLM):
-hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "modular_model_index.json" "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
+hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
 
 # Or a single task family:
-hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "modular_model_index.json" "FL2VA/*" --local-dir MiniMax-H3
+hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" --local-dir MiniMax-H3
 ```
 
 diffusers users do not need a manual download: `ModularPipeline.from_pretrained("MiniMaxAI/MiniMax-H3")` fetches exactly the components it needs. See the [diffusers documentation](https://github.com/huggingface/diffusers/blob/minimax-h3/docs/source/en/api/pipelines/minimax_h3.md) for loading recipes.

model_index.json

@@ -2,14 +2,6 @@
   "_class_name": "MiniMaxH3ModularPipeline",
   "_diffusers_version": "0.36.0.dev0",
   "_blocks_class_name": "MiniMaxH3Blocks",
-  "_minimax_h3": {
-    "schema_version": 1,
-    "index_scope": "repository",
-    "task_family_indexes": {
-      "fl2va": "FL2VA/model_index.json",
-      "ref2va": "Ref2VA/model_index.json"
-    }
-  },
   "text_encoder": [
     "transformers",
     "Qwen3VLForConditionalGeneration",