Spaces:
Configuration error
Configuration error
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,5 +6,20 @@ colorTo: gray
|
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
|
|
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
+
# 👀 On-Device LLM Research
|
| 10 |
|
| 11 |
+
We are the **SK Devocean On-Device LLM (Large Language Model) Team**.
|
| 12 |
+
Our goal is to enable **LLMs to run efficiently on mobile and edge devices** through model compression, optimization, pruning, and quantization.
|
| 13 |
+
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
## 🚀 Focus Areas
|
| 17 |
+
- **Model Compression & Optimization**: quantization, pruning, knowledge distillation
|
| 18 |
+
- **On-Device AI Services**: spam filtering, summarization, translation, and more real-world applications
|
| 19 |
+
- **Open Research Sharing**: publishing experimental results and models as open source
|
| 20 |
+
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
## 🌐 Vision
|
| 24 |
+
We envision a world where powerful AI models run **securely and efficiently on personal devices**,
|
| 25 |
+
without relying on the cloud.
|