Revert to 713c1a6a33a2

.gitattributes

@@ -47,6 +47,3 @@ DeepGen_CKPT.zip.part-00007 filter=lfs diff=lfs merge=lfs -text
 DeepGen_CKPT.zip.part-00008 filter=lfs diff=lfs merge=lfs -text
 DeepGen_CKPT.zip.part-00009 filter=lfs diff=lfs merge=lfs -text
 DeepGen_CKPT.zip.part-00010 filter=lfs diff=lfs merge=lfs -text
-docs/bubble_chart.png filter=lfs diff=lfs merge=lfs -text
-docs/arch.png filter=lfs diff=lfs merge=lfs -text
-docs/teaser.png filter=lfs diff=lfs merge=lfs -text

DeepGen_CKPT.zip.part-00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f94464b6b16f559dc6b09e31c2abe020a7cd7f1de4c4d5b046e307c1814776
+size 5368709120

DeepGen_CKPT.zip.part-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca0fd771ae4061dc2d0d36f62b50bca675beab9b3dca424119d828a1b23b28e
+size 5368709120

DeepGen_CKPT.zip.part-00002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16671fcd9f92a879b831d2297a281757b473546ab758679a170de792abd787b6
+size 5368709120

DeepGen_CKPT.zip.part-00003

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8022e2693aa690ad14e184616d7ef0d49dd519fc423a71582aa9c8d10b2136f
+size 5368709120

DeepGen_CKPT.zip.part-00004

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fd4a4c59212d45a35006f4b4dcd03f8dec684c46d852f3b720dff0bdddd9a4
+size 5368709120

DeepGen_CKPT.zip.part-00005

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0fba2bd69be06c705779a6c1a9a1d41366e0310ef696eae944872083109a2a
+size 5368709120

DeepGen_CKPT.zip.part-00006

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9573c3dc0d980450fc8e51e19b9c36971bf16d91ea560a9a9edf54824b672b
+size 5368709120

DeepGen_CKPT.zip.part-00007

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb739f5b16b92057487b7e9055119fb532872caf9857c13f76ea49fa45832ea
+size 5368709120

DeepGen_CKPT.zip.part-00008

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4eac2c5010cc7067f556344eaa4e93e1b6df1986eeaa9ced1aa4f20e3411f0
+size 5368709120

DeepGen_CKPT.zip.part-00009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9cd1e26bcb9ca5dba536c1e86bde3619c3f8f9d0bb80fa705994bbdcb7c4f00
+size 5368709120

DeepGen_CKPT.zip.part-00010

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce439a0e4c6dea344e5736e2b09dd17e835047eda9757eb58ebca485f27f506
+size 1993873384

README.md

@@ -7,14 +7,6 @@ base_model:
 pipeline_tag: image-to-image
 ---
 
-> **DeepGen 1.0 Checkpoints**
->
-> | Stage | Repository | Description |
-> | :--- | :--- | :--- |
-> | Pretrain | [deepgenteam/DeepGen-1.0-Pretrain](https://huggingface.co/deepgenteam/DeepGen-1.0-Pretrain) | Alignment pre-training checkpoint |
-> | SFT | [deepgenteam/DeepGen-1.0-SFT](https://huggingface.co/deepgenteam/DeepGen-1.0-SFT) | Supervised fine-tuning checkpoint |
-> | **RL** | **[deepgenteam/DeepGen-1.0](https://huggingface.co/deepgenteam/DeepGen-1.0)** | Reinforcement learning checkpoint (MR-GDPO) *(this repo)* |
-
 # 💡 DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
 <p align="left">
   <a href="http://arxiv.org/abs/2602.12205">
@@ -37,14 +29,14 @@ pipeline_tag: image-to-image
   </a>
 </p>
 DeepGen 1.0 is a lightweight unified multimodal model with only 5B parameters (3B VLM + 2B DiT). It integrates five core capabilities—general image generation, general image editing, reasoning image generation, reasoning image editing, and text rendering—within a single model. Across multiple authoritative benchmarks, DeepGen 1.0 is competitive with competitive with or surpassing the state-of-the-art unified multimodal models that are 3× to 16× larger, achieving comprehensive performance, demonstrating that massive scaling is not the sole path to high-performance multimodal generation.
-<p align="left"><img src="docs/bubble_chart.png" width="80%"></p>
+<p align="left"><img src="bubble_chart.png" width="80%"></p>
 
 ## 🧠 Method
 Our core observation is that a lightweight model, when empowered by synergistic architecture design and data-centric training strategies, can achieve comprehensive capabilities competitive with or even surpassing much larger counterparts.
 To overcome the limitations of lightweight models in semantic understanding and fine-grained control, we introduce **Stacked Channel Bridging (SCB)**, a deep alignment framework that extracts hierarchical features from multiple VLM layers and fuses them with learnable ``think tokens'' to provide the generative backbone with structured, reasoning-rich guidance. 
 We further design a data-centric training strategy spanning three progressive stages: (1) **Alignment Pre-training** on large-scale image-text pairs and editing triplets to synchronize VLM and DiT representations, (2) **Joint Supervised Fine-tuning** on a high-quality mixture of generation, editing, and reasoning tasks to foster omni-capabilities, and (3) **Reinforcement Learning with MR-GRPO**, which leverages a mixture of reward functions and supervision signals, resulting in substantial gains in generation quality and alignment with human preferences, while maintaining stable training progress and avoiding visual artifacts.
 
-<p align="left"><img src="docs/arch.png" width="80%"></p>
+<p align="left"><img src="arch.png" width="80%"></p>
 
 ## 📊 Benchmarks
 
@@ -99,18 +91,16 @@ We further design a data-centric training strategy spanning three progressive st
 | **DeepGen 1.0 (RL)** | **3B + 2B** | 10.8 🥉 | 75.7 🥈 |
 
 ## 🎨 Quantitative results
-<p align="left"><img src="docs/teaser.png" width="80%"></p>
+<p align="left"><img src="teaser.png" width="80%"></p>
 
 ## 🛠️ Usage
 
-### Download Checkpoint
-This repository contains the **Reinforcement Learning (MR-GDPO)** checkpoint — the final release model.
+### Merge ZIP Files
+To use the DeepGen checkpoints, please merge the sharded model files first. We release Pre-traning, Supervised Fine-Tuning and Reinforcement Learning checkpoints.
 
 ```bash
-# Using hf CLI
-hf download deepgenteam/DeepGen-1.0 model.pt --local-dir .
-
-# Or using Python
-from huggingface_hub import hf_hub_download
-hf_hub_download("deepgenteam/DeepGen-1.0", "model.pt", local_dir=".")
-```
+# Merge zip
+cat DeepGen_CKPT.zip.part-* > DeepGen_CKPT.zip
+# Unzip DeepGen checkpoints 
+unzip DeepGen_CKPT.zip
+```