Update README.md
Browse files
README.md
CHANGED
|
@@ -11,30 +11,37 @@ license: apache-2.0
|
|
| 11 |
</p>
|
| 12 |
|
| 13 |
|
| 14 |
-
|
| 15 |
-
|
| 16 |
## ๐ Update News
|
| 17 |
- **2026-03-05**: Official release of KORMo-Diffusion.
|
| 18 |
- **2026-03-02**: Official release of KORMo-VL.
|
| 19 |
- **2025-10-13**: Official release of KORMo-10B-sft.
|
| 20 |
---
|
| 21 |
-
## ๐ก About KORMo-VL
|
| 22 |
-
KORMo-Diffusion์ ๋ํด์...
|
| 23 |
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
</video>
|
| 27 |
-
---
|
| 28 |
|
| 29 |
-
|
|
|
|
| 30 |
|
| 31 |
-
-
|
| 32 |
-
|
| 33 |
-
- ๐ป **GitHub Repository**: [๐ Training and Inference Code](https://github.com/MLP-Lab/KORMo-tutorial)
|
| 34 |
-
- ๐ **Tutorial**: [๐ Instruction Tuning over google colab](https://colab.research.google.com/github/MLP-Lab/KORMo-tutorial/blob/main/tutorial/02.sft_qlora.ipynb) [๐ Youtube Tutorial](https://www.youtube.com/@MLPLab)
|
| 35 |
|
| 36 |
---
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
## ๐ T2I Performance
|
| 40 |
|
|
|
|
| 11 |
</p>
|
| 12 |
|
| 13 |
|
|
|
|
|
|
|
| 14 |
## ๐ Update News
|
| 15 |
- **2026-03-05**: Official release of KORMo-Diffusion.
|
| 16 |
- **2026-03-02**: Official release of KORMo-VL.
|
| 17 |
- **2025-10-13**: Official release of KORMo-10B-sft.
|
| 18 |
---
|
| 19 |
+
## ๐ก About KORMo-VL-Diffusion
|
|
|
|
| 20 |
|
| 21 |
+
**KORMo-VL** is a vision-language model developed **from scratch by the KAIST MLP Lab (https://sites.google.com/view/aailab)**, built on top of **KORMo-10B**.
|
| 22 |
+
The system consists of two components:
|
|
|
|
|
|
|
| 23 |
|
| 24 |
+
* **Vision-Language Model (VLM)**
|
| 25 |
+
* **Image Generation Model**
|
| 26 |
|
| 27 |
+
The KORMo-VL-Diffusion model, designed for image generation, was trained from scratch with a high proportion of images reflecting Korean daily environments and culture.
|
| 28 |
+
<span style="color:red">Unfortunately, due to limited GPU resources during the research process, we are sharing the intermediate results of the model at this stage.</span>
|
|
|
|
|
|
|
| 29 |
|
| 30 |
---
|
| 31 |
|
| 32 |
+
KORMo-VL์ KAIST MLP ์ฐ๊ตฌ์ค์์ **from scratch๋ก ๊ฐ๋ฐํ ์๊ฐ-์ธ์ด ๋ชจ๋ธ**๋ก, KORMo-10B๋ฅผ ๊ธฐ๋ฐ์ผ๋ก (1) ์๊ฐ-์ธ์ด ๋ชจ๋ธ๊ณผ (2) ์ด๋ฏธ์ง ์์ฑ ๋ชจ๋ธ๋ก ๊ตฌ์ฑ๋์ด ์์ต๋๋ค.
|
| 33 |
+
|
| 34 |
+
์ด ์ค **์ด๋ฏธ์ง ์์ฑ์ ์ํ KORMo-VL-Diffusion** ๋ชจ๋ธ์ ํ๊ตญ์ ์ํ ํ๊ฒฝ๊ณผ ๋ฌธํ๋ฅผ ๋ฐ์ํ๊ธฐ ์ํด ๊ตญ๋ด ํ๊ฒฝ ์ด๋ฏธ์ง๋ฅผ ๊ฐ๋ฅํ ๋์ ๋น์จ๋ก ์ฌ์ฉํ์ฌ **from scratch๋ถํฐ ํ์ต๋ ๋ชจ๋ธ**์
๋๋ค.
|
| 35 |
+
<span style="color:red">๋ค๋ง ์ฐ๊ตฌ ์งํ ์ค GPU ์์์ ์ถ๊ฐ๋ก ํ๋ณดํ์ง ๋ชปํด **ํ์ฌ๋ ์ค๊ฐ ๊ฒฐ๊ณผ๋ฌผ์ ๊ณต์ ํ๊ฒ ๋์์ต๋๋ค.**</span>
|
| 36 |
+
|
| 37 |
+
* **LLM:** KORMo-VL
|
| 38 |
+
* **Languages:** Korean / English
|
| 39 |
+
* **Training Data:** Synthetic data + public datasets (e.g., AI Hub, details to be released)
|
| 40 |
+
|
| 41 |
+
ํฅํ ํด๋น ๋ชจ๋ธ์ ์ถฉ๋ถํ ํ์ตํ ์ ์๋ ํ๊ฒฝ์ด ๋ง๋ จ๋๋ค๋ฉด **์์ฑ๋ ๋ชจ๋ธ๋ก ๋ฐ์ ์ํค๋ ๊ฒ์ ๋ชฉํ๋ก ํ๊ณ ์์ต๋๋ค.**
|
| 42 |
+
์ค๊ฐ ๊ฒฐ๊ณผ๋ฌผ ์์์ ์ถ๊ฐ ํ๋์ด๋ ์ฐ๊ตฌ๋ฅผ ์งํํ๊ณ ์ถ์ ๋ถ๋ค์ **์์ ๋กญ๊ฒ ํ์ฉํด ๋ณด์๊ธฐ ๋ฐ๋๋๋ค.**
|
| 43 |
+
|
| 44 |
+
|
| 45 |
|
| 46 |
## ๐ T2I Performance
|
| 47 |
|