openfree commited on
Commit
87c00bf
·
verified ·
1 Parent(s): 8799bcc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -1
README.md CHANGED
@@ -8,8 +8,25 @@ base_model:
8
  - Qwen/Qwen3-4B-Instruct-2507
9
  - Qwen/Qwen3-4B-Thinking-2507
10
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  # openfree/Darwin-Qwen3-4B
12
- This model is automatically merged using evolutionary algorithm v3.2
13
 
14
  # Overview
15
  This study introduces a new paradigm of AI model fusion. Traditional "model merging" techniques have been restricted to models of the same family (e.g., transformer-based LLMs). We transcend this limitation by proposing a method to directly collide and fuse the core representational structures (DNA) of entirely different species — such as transformers and diffusion models. This approach acts as an "AI particle accelerator," colliding fundamentally distinct elements of intelligence to uncover new possibilities.
 
8
  - Qwen/Qwen3-4B-Instruct-2507
9
  - Qwen/Qwen3-4B-Thinking-2507
10
  ---
11
+
12
+ <div align="center">
13
+ <span style="font-family: default; font-size: 1.5em;">Gemma-3-R1984-27B</span>
14
+ <div>
15
+ evolutionary algorithm 'Darwin A2AP' 🤔
16
+ </div>
17
+ </div>
18
+ <br>
19
+ <div align="center" style="line-height: 1;">
20
+ <a href=" https://discord.gg/openfreeai" style="margin: 2px;">
21
+ <img alt="OpenFree AI Discord Server" src="https://img.shields.io/badge/Discord-000000?style=for-the-badge&logo=discord&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
22
+ </a>
23
+ <a href="https://huggingface.co/VIDraft" style="margin: 2px;">
24
+ <img alt="HF Page" src="https://img.shields.io/badge/VIDraft-fcd022?style=for-the-badge&logo=huggingface&logoColor=000&labelColor" style="display: inline-block; vertical-align: middle;"/>
25
+ </a>
26
+ </div>
27
+
28
  # openfree/Darwin-Qwen3-4B
29
+ This model is automatically merged using evolutionary algorithm 'Darwin A2AP' v3.2
30
 
31
  # Overview
32
  This study introduces a new paradigm of AI model fusion. Traditional "model merging" techniques have been restricted to models of the same family (e.g., transformer-based LLMs). We transcend this limitation by proposing a method to directly collide and fuse the core representational structures (DNA) of entirely different species — such as transformers and diffusion models. This approach acts as an "AI particle accelerator," colliding fundamentally distinct elements of intelligence to uncover new possibilities.