Update README.md
Browse files
README.md
CHANGED
@@ -43,7 +43,7 @@ model-index:
|
|
43 |
## A.X 3.1 Light Highlights
|
44 |
|
45 |
<!-- SK Telecom released **A.X 3.1 Light** (pronounced "A dot X"), a large language model (LLM) optimized for Korean-language understanding and enterprise deployment, on July 10, 2025. -->
|
46 |
-
**A.X 3.1 Light** (pronounced "A dot X"
|
47 |
This sovereign AI model was developed entirely in-house by SKT, encompassing model architecture, data curation, and training, all carried out on SKT’s proprietary supercomputing infrastructure, TITAN.
|
48 |
The model was trained from scratch on a high-quality multilingual corpus comprising **1.65 trillion tokens**, with a primary focus on the Korean language.
|
49 |
With a strong emphasis on data quality, A.X 3.1 Light achieves **Pareto-optimal performance among Korean LLMs relative to its training corpus size**, enabling **highly efficient and cost-effective compute usage**.
|
|
|
43 |
## A.X 3.1 Light Highlights
|
44 |
|
45 |
<!-- SK Telecom released **A.X 3.1 Light** (pronounced "A dot X"), a large language model (LLM) optimized for Korean-language understanding and enterprise deployment, on July 10, 2025. -->
|
46 |
+
**A.X 3.1 Light** (pronounced "A dot X") is a light weight LLM optimized for Korean-language understanding and enterprise deployment.
|
47 |
This sovereign AI model was developed entirely in-house by SKT, encompassing model architecture, data curation, and training, all carried out on SKT’s proprietary supercomputing infrastructure, TITAN.
|
48 |
The model was trained from scratch on a high-quality multilingual corpus comprising **1.65 trillion tokens**, with a primary focus on the Korean language.
|
49 |
With a strong emphasis on data quality, A.X 3.1 Light achieves **Pareto-optimal performance among Korean LLMs relative to its training corpus size**, enabling **highly efficient and cost-effective compute usage**.
|