Point the model card at the GitHub repo instead of local usage commands

Drop the inference snippet so usage stays in the code repository. Mention the 4B image-to-3D checkpoint.

README.md

@@ -1,6 +1,5 @@
 ---
 license: apache-2.0
-library_name: transformers
 pipeline_tag: image-to-3d
 tags:
   - 3d
@@ -23,62 +22,35 @@ papers:
 
 **CG-MLLM: Captioning and Generating 3D Content via Multi-modal Large Language Models** (ICML 2026)
 
-CG-MLLM is a 3D multimodal large language model (3D MLLM) built upon Qwen3-VL and Hunyuan3D-2.1 VAE for unified **3D understanding**, **3D captioning**, and **high-resolution 3D content generation**.
+CG-MLLM is a 3D multimodal large language model built on a **Qwen3-VL** backbone and a Hunyuan3D-2.1 VAE, for 3D captioning and 3D generation.
 
-It uses a Mixture-of-Transformer design: a TokenAR Transformer for token-level content and a BlockAR Transformer for block-level 3D latents, enabling long-context interaction between standard tokens and spatial blocks in one architecture.
+This repository is the **v0.1 multi-task** checkpoint, on **Qwen3-VL-2B-Instruct**. It covers image-to-3D, text-to-3D, image understanding, and 3D understanding.
+
+The **4B image-to-3D** checkpoint (Qwen3-VL-4B, specialized on HY3D-Bench) is at [JreamH/CGMLLM-4B-i2o](https://huggingface.co/JreamH/CGMLLM-4B-i2o).
 
 ## Links
 
+- **Code (how to run):** https://github.com/dreaming-huang/CG-MLLM
 - **Paper (arXiv):** https://arxiv.org/abs/2601.21798
 - **Hugging Face Papers:** https://huggingface.co/papers/2601.21798
 - **Project page:** https://cv.jream.top/CG-MLLM-page/
-- **Code:** https://github.com/dreaming-huang/CG-MLLM
 - **ICML poster:** https://icml.cc/virtual/2026/poster/63909
 
 ## Model Details
 
 | Item | Value |
 | --- | --- |
-| Version | v0.1 |
-| Architecture | Mixture-of-Transformer (TokenAR + BlockAR) |
+| Version | v0.1, multi-task |
 | Vision-language backbone | Qwen3-VL-2B-Instruct |
 | 3D latent tokenizer | Hunyuan3D-2.1 VAE |
 | Tasks | Image-to-3D, text-to-3D, image understanding, 3D understanding |
+| Checkpoint file | `ema.safetensors` |
 | Venue | ICML 2026 |
 | License | Apache-2.0 |
 | Authors | Junming Huang, Chi Wang, Letian Li, Guangkai Xu, Donglin Huang, Hao Chen, Qiang Dai, Weiwei Xu |
 | Affiliations | Zhejiang University; LIGHTSPEED |
 
-## Repository Contents
-
-| File | Description |
-| --- | --- |
-| `ema.safetensors` | EMA checkpoint weights for CG-MLLM v0.1 |
-
-## How to Use
-
-Install and run inference from the [official code repository](https://github.com/dreaming-huang/CG-MLLM):
-
-```bash
-git clone https://github.com/dreaming-huang/CG-MLLM.git
-cd CG-MLLM
-# follow Installation in the GitHub README, then:
-hf download JreamH/CGMLLM ema.safetensors --local-dir models/CGMLLM
-```
-
-Example (image-to-3D):
-
-```bash
-python inference.py \
-  --llm_base_path Qwen/Qwen3-VL-2B-Instruct \
-  --checkpoint models/CGMLLM \
-  --obj_vae_path tencent/Hunyuan3D-2.1 \
-  --obj_vae_len 4096 \
-  --use_qwen_vit --use_qwen_vl --qk_norm \
-  --mode i2obj --image examples/chairo.png
-```
-
-See the GitHub README for text-to-3D, image understanding, and 3D understanding examples.
+Usage is documented in the [GitHub repository](https://github.com/dreaming-huang/CG-MLLM). This card does not duplicate the inference commands.
 
 ## Citation
 
@@ -95,4 +67,4 @@ If you find this work useful, please cite:
 
 ## Acknowledgments
 
-Inference code builds on [BAGEL](https://github.com/ByteDance-Seed/Bagel) and the [Hunyuan3D-2.1](https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1) shape VAE. Please follow their licenses when using those components.
+This work builds on [Qwen3-VL](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct), [BAGEL](https://github.com/ByteDance-Seed/Bagel), and the [Hunyuan3D-2.1](https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1) shape VAE. Please follow their licenses when using those components.