ko-wand-136M
ko-wand-136M๋ insturctkr์์ ์ฌ์ ํ์ตํ SLM์ ๋๋ค.
Model Description
maywell/korean_textbooks์ ํ๊ตญ์ด ๋ง๋ญ์น๋ฅผ ์ด์ฉํ์ฌ ์ฌ์ ํ์ต ๋์์ต๋๋ค.
Model Info
๋ฏธ์คํธ๋ ์ํคํ ์ณ๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ์์ ํ ๋๋ค ๊ฐ์ค์น๋ฅผ ์์์ผ๋ก ์ฌ์ ํ์ต ๋ ๋ชจ๋ธ์ ๋๋ค. Instruction ํ๋๋์ง ์์์ต๋๋ค.
Training Details
| Batch Size | Token Seen | lr |
|---|---|---|
| 1024 | 2.5B | 2e-3 (cosine) |
License
apache-2.0
- Downloads last month
- 704
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.