---
title: SkyJM-Gen-4B
canonical_url: "https://www.modelscope.ai/models/SKYLENAGE/SkyJM-Gen-4B"
md_url: "https://www.modelscope.ai/models/SKYLENAGE/SkyJM-Gen-4B.md"
repository: SKYLENAGE/SkyJM-Gen-4B
last_updated: 2026-06-24
license: apache-2.0
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
parameters: 5.2B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 102
stars: 0
---

# SkyJM-Gen-4B

> SkyJM-Gen-4B - An open-source model by SKYLENAGE on ModelScope. SkyJM（RubricRM） is a reward model for visual generation, covering both text-to-image generation and image editing. Given a prompt and two candidate images, it predicts which one better satisfies…

SKYLENAGE/SkyJM-Gen-4B is a 5.2B-parameter machine learning model on ModelScope. licensed under apache-2.0.

- **Repository**: SKYLENAGE/SkyJM-Gen-4B
- **License**: apache-2.0
- **Parameters**: 5.2B
- **Downloads**: 102
- **Stars**: 0
- **Last updated**: 2026-06-24

Source: https://www.modelscope.ai/models/SKYLENAGE/SkyJM-Gen-4B

---

**SkyJM**（RubricRM） is a reward model for visual generation, covering both **text-to-image generation** and **image editing**. Given a prompt and two candidate images, it predicts which one better satisfies the instruction. RubricRM performs the following in a single forward pass:

- Dynamically produces an evaluation **rubric** conditioned on the prompt — including evaluation dimensions, per-dimension weights, and graded scoring descriptors;
- Scores both candidate images at the **dimension level** under that rubric;
- Aggregates the dimension scores via the rubric weights to derive the final preference.

We release two model sizes built on the Qwen3.5 backbone:

- `SkyJM-Gen-4B` / `SkyJM-Gen-9B` — for text-to-image generation
- `SkyJM-Edit-4B` / `SkyJM-Edit-9B` — for image editing

## Performance

### Text-to-image generation

| Model | MMRB2 | GenAI-Bench | GenAI-Bench-Verified |
|---|:---:|:---:|:---:|
| *Proprietary MLLMs* | | | |
| Claude Sonnet 4.6 | 70.8 | 65.8 | 75.3 |
| GPT-5.4 | 67.5 | 64.2 | 74.2 |
| Gemini 2.5 Pro | 70.5 | 67.8 | 77.4 |
| Gemini 3.1 Pro | 74.4 | 73.9 | 84.8 |
| *Open-source MLLMs* | | | |
| Qwen3-VL-8B | 61.2 | 63.3 | 72.5 |
| Qwen3-VL-235B-A22B | 66.6 | 61.5 | 69.7 |
| Qwen3.5-9B | 66.3 | 63.3 | 70.7 |
| Qwen3.5-397B-A17B | 72.7 | 66.2 | 77.0 |
| *Reward Models* | | | |
| HPSv2 | 55.0 | 68.8 | 78.1 |
| PickScore | 57.6 | 70.0 | 79.2 |
| HPSv3 | 60.2 | 70.9 | 81.0 |
| UnifiedReward-9B | 57.9 | 69.2 | 72.8 |
| UnifiedReward-Think-9B | 65.5 | 72.8 | 81.7 |
| UnifiedReward-Flex-8B | 69.2 | <u>73.4</u> | <u>84.2</u> |
| **SkyJM-Gen-4B** (Ours) | <u>70.5</u> | 73.2 | 83.1 |
| **SkyJM-Gen-9B** (Ours) | **72.0** | **74.1** | **84.5** |

### Image editing

| Model | MMRB2 | EditReward-ERB Avg | EditScore-ERB Avg |
|---|:---:|:---:|:---:|
| *Proprietary MLLMs* | | | |
| Claude Sonnet 4.6 | 71.7 | 44.1 | 79.3 |
| GPT-5.4 | 68.5 | 42.5 | 74.6 |
| Gemini 2.5 Pro | 71.3 | 42.2 | 75.2 |
| Gemini 3.1 Pro | 74.9 | 45.0 | 81.6 |
| *Open-source MLLMs* | | | |
| Qwen3-VL-8B | 63.4 | 40.9 | 76.9 |
| Qwen3-VL-235B-A22B | 64.8 | 34.6 | 78.8 |
| Qwen3.5-9B | 64.4 | 37.4 | 72.0 |
| Qwen3.5-397B-A17B | 73.7 | 43.9 | 81.2 |
| *Reward Models* | | | |
| EditReward-7B | 67.2 | 38.4 | 78.3 |
| EditScore-7B | 55.6 | 28.8 | 61.9 |
| **SkyJM-Edit-4B** (Ours) | <u>73.2</u> | <u>45.5</u> | <u>85.5</u> |
| **SkyJM-Edit-9B** (Ours) | **75.4** | **46.4** | **85.6** |

## Training Strategy

**Stage 1: Rubric-trajectory SFT.** We use Gemini 3.1 Pro to synthesize rubric-based evaluation trajectories conditioned on human preference labels, then filter them with structural and label-consistency checks for SFT.

**Stage 2: Dimension-level GRPO.** During RL, we fix the rubric and optimize only the scoring process using rewards based on per-dimension score gaps, with saturated-group filtering to suppress noisy low-variance updates.


## Quick Start

For detailed usage instructions, installation guide, and inference examples (supporting both vLLM and Transformers backends), please refer to the official inference framework:

**[SKYLENAGE-JUDGER](https://github.com/SKYLENAGE-AI/SKYLENAGE-JUDGER)** — Unified inference framework for SkyJM judge models.

## Link
  - **GitHub**: [SKYLENAGE-AI/SKYLENAGE-JUDGER](https://github.com/SKYLENAGE-AI/SKYLENAGE-JUDGER)
  - **Hugging Face Models**:
    - [skylenage-ai/SkyJM-Gen-4B](https://huggingface.co/skylenage-ai/SkyJM-Gen-4B)
    - [skylenage-ai/SkyJM-Gen-9B](https://huggingface.co/skylenage-ai/SkyJM-Gen-9B)
    - [skylenage-ai/SkyJM-Edit-4B](https://huggingface.co/skylenage-ai/SkyJM-Edit-4B)
    - [skylenage-ai/SkyJM-Edit-9B](https://huggingface.co/skylenage-ai/SkyJM-Edit-9B)
  - **Hugging Face Dataset**: [skylenage-ai/RubricRM-Data](https://huggingface.co/datasets/skylenage-ai/RubricRM-Data)
  - **ModelScope Models**:
    - [SKYLENAGE/SkyJM-Gen-4B](https://www.modelscope.cn/models/SKYLENAGE/SkyJM-Gen-4B)
    - [SKYLENAGE/SkyJM-Gen-9B](https://www.modelscope.cn/models/SKYLENAGE/SkyJM-Gen-9B)
    - [SKYLENAGE/SkyJM-Edit-4B](https://www.modelscope.cn/models/SKYLENAGE/SkyJM-Edit-4B)
    - [SKYLENAGE/SkyJM-Edit-9B](https://www.modelscope.cn/models/SKYLENAGE/SkyJM-Edit-9B)