---
title: SimArt
canonical_url: "https://www.modelscope.cn/models/bytedance-community/SimArt"
md_url: "https://www.modelscope.cn/models/bytedance-community/SimArt.md"
repository: bytedance-community/SimArt
last_updated: 2026-06-05
license: apache-2.0
parameters: 8.8B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 6
stars: 0
---

# SimArt

> SimArt - bytedance-community 在 ModelScope 开源的模型。This directory contains the pretrained weights for the SIMART models.

bytedance-community/SimArt 是 ModelScope 魔搭社区上的 8.8B 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: bytedance-community/SimArt
- **License**: apache-2.0
- **Parameters**: 8.8B
- **Downloads**: 6
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/bytedance-community/SimArt

---

# SIMART Checkpoints

This directory contains the pretrained weights for the SIMART models.

## Directory Structure

### `simart_mllm/`
- **Description**: This directory contains the weights for the Multi-Modal Large Language Model (MLLM). 
- **Base Model**: Fine-tuned from `Qwen3-VL-8B` (or similar Qwen-VL architecture).
- **Purpose**: Used for generating articulated 3D object structures (URDF files) based on multi-modal inputs.

### `simart_vqvae/`
- **Description**: This directory contains the weights for the Sparse VQ-VAE model.
- **Purpose**: Used for encoding and decoding 3D part geometries into/from discrete latent spaces.
- **Contents**:
  - `encoder.pt`: Weights for the VQ-VAE encoder.
  - `vq.pt`: Weights for the Vector Quantizer (codebook).
  - `decoder.pt`: Weights for the VQ-VAE decoder.