Hugging Face's logo

Spaces:
Skywork
/
README
Configuration error

App Files Community
OrlandoHugBot commited on
Commit
aad9951
·
verified ·
1 Parent(s): ed704cc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -31
README.md CHANGED
@@ -3,34 +3,35 @@ Welcome to **Skywork**! We are an innovative research team dedicated to advancin
3
  The name **“Skywork”** combines the limitless potential of the **Sky** with the impactful outcomes of our **Work**.
4
 
5
  ---
6
-
7
- ## Models
8
- - **[Skywork-UniPic3](https://github.com/SkyworkAI/UniPic)**: Unified Multi-Image Composition with Sequence Modeling
9
-
10
- - **[Skywork-R1V4](https://huggingface.co/papers/2512.02395)**: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
11
-
12
- - **[Skywork-UniPic2](https://huggingface.co/Skywork/UniPic2-Metaquery-9B)**: Building Kontext Model with Online RL for Unified Multimodal Model
13
-
14
- - **[Skywork-UniPic](https://huggingface.co/Skywork/Skywork-UniPic-1.5B)**: Unified Autoregressive Modeling for Visual Understanding and Generation
15
-
16
- - **[Skywork-R1V3-38B](https://huggingface.co/Skywork/Skywork-R1V3-38B)**: Advanced Multimodal Reasoning Model
17
-
18
- - **[Skywork-Reward-V2 series](https://huggingface.co/collections/Skywork/skywork-reward-v2-685cc86ce5d9c9e4be500c84)**: Scaling Preferenec Data Curation to the Extreme
19
-
20
- - **[Skywork-SWE-32B](https://huggingface.co/Skywork/Skywork-SWE-32B)**: Unveiling Data Scaling Laws for Software Engineering in LLMs
21
-
22
- - **[Skywork-OR1](https://huggingface.co/collections/Skywork/skywork-or1-67fa1bcb41b436ef2def76b9)**: SOTA 7B and 32B Open Reasoning Models for Math and Code
23
-
24
- - **[Skywork-R1V2-38B](https://huggingface.co/Skywork/Skywork-R1V2-38B)**: Multimodal Hybrid Reinforcement Learning for Reasoning
25
-
26
- - **[Skywork-VL-Reward-7B](https://huggingface.co/Skywork/Skywork-VL-Reward-7B)**: MultiModal Reward Model
27
-
28
- - **[Skywork-R1V-38B](https://huggingface.co/Skywork/Skywork-R1V-38B)**: Pioneering Multimodal Reasoning with Chain-of-Thought
29
-
30
- - **[SkyReels-V1](https://huggingface.co/Skywork/SkyReels-V1)**: Human-Centric Video Foundation Model
31
-
32
- - **[SkyReels-AX](https://huggingface.co/collections/Skywork/skyreels-ax-67fb4711700c4e2c0551f930)**: Controllable Video Generation Series
33
-
34
- - **[Skywork-o1-Open-PRM](https://huggingface.co/Skywork/Skywork-o1-Open-PRM-Qwen-2.5-1.5B)**: o1 Open Model Series
35
-
36
- - **[Skywork-Reward series](https://huggingface.co/collections/Skywork/skywork-reward-model-66d7fbdebae0e60d00a6b60d)**: Strong 8B and 27B Reward Models Topping RewardBench
 
 
3
  The name **“Skywork”** combines the limitless potential of the **Sky** with the impactful outcomes of our **Work**.
4
 
5
  ---
6
+ ## Skywork Model Zoo
7
+ ---
8
+ ### 🧠 Multimodal Reasoning & Agentic Intelligence (R1V Series)
9
+ | | |
10
+ |---|---|
11
+ | **[Skywork-R1V4](https://huggingface.co/papers/2512.02395)**<br/>Agentic Multimodal Intelligence with Interleaved Thinking | **[Skywork-R1V3-38B](https://huggingface.co/Skywork/Skywork-R1V3-38B)**<br/>Advanced Multimodal Reasoning |
12
+ | **[Skywork-R1V2-38B](https://huggingface.co/Skywork/Skywork-R1V2-38B)**<br/>Hybrid RL for Multimodal Reasoning | **[Skywork-R1V-38B](https://huggingface.co/Skywork/Skywork-R1V-38B)**<br/>Chain-of-Thought Multimodal Reasoning |
13
+
14
+
15
+ ### 🧩 Unified Multimodal Generation & Composition (UniPic Series)
16
+ | | |
17
+ |---|---|
18
+ | **[Skywork-UniPic3](https://github.com/SkyworkAI/UniPic)**<br/>Unified Multi-Image Composition with Sequence Modeling | **[Skywork-UniPic2](https://huggingface.co/Skywork/UniPic2-Metaquery-9B)**<br/>Kontext Model with Online RL |
19
+ | **[Skywork-UniPic](https://huggingface.co/Skywork/Skywork-UniPic-1.5B)**<br/>Unified Autoregressive Vision–Language Model | |
20
+
21
+ ### 🧮 Open Reasoning for Math & Code
22
+ | | |
23
+ |---|---|
24
+ | **[Skywork-OR1](https://huggingface.co/collections/Skywork/skywork-or1-67fa1bcb41b436ef2def76b9)**<br/>Open Reasoning Models (7B / 32B) | **[Skywork-SWE-32B](https://huggingface.co/Skywork/Skywork-SWE-32B)**<br/>Scaling Laws for Software Engineering |
25
+
26
+ ### 🎯 Reward Modeling & Preference Learning
27
+ | | |
28
+ |---|---|
29
+ | **[Skywork-Reward-V2 Series](https://huggingface.co/collections/Skywork/skywork-reward-v2-685cc86ce5d9c9e4be500c84)**<br/>Extreme-Scale Preference Data Curation | **[Skywork-Reward Series](https://huggingface.co/collections/Skywork/skywork-reward-model-66d7fbdebae0e60d00a6b60d)**<br/>Top RewardBench Models |
30
+ | **[Skywork-VL-Reward-7B](https://huggingface.co/Skywork/Skywork-VL-Reward-7B)**<br/>Multimodal Reward Model | **[Skywork-o1-Open-PRM](https://huggingface.co/Skywork/Skywork-o1-Open-PRM-Qwen-2.5-1.5B)**<br/>Open PRM Series |
31
+
32
+ ### 🎬 Video Foundation & Generation (SkyReels Series)
33
+ | | |
34
+ |---|---|
35
+ | **[SkyReels-V1](https://huggingface.co/Skywork/SkyReels-V1)**<br/>Human-Centric Video Foundation Model | **[SkyReels-AX](https://huggingface.co/collections/Skywork/skyreels-ax-67fb4711700c4e2c0551f930)**<br/>Controllable Video Generation |
36
+
37
+ ---