Update README.md
Browse files
README.md
CHANGED
|
@@ -45,7 +45,10 @@ gemma-2-27b-it ๋ฒ ์ด์ค๋ชจ๋ธ์ ์ฌ์ฉํด์ H100-80G 8๊ฐ๋ฅผ ํตํด CPT(Conti
|
|
| 45 |
-ํ ํฌ๋์ด์ ๋ ๋จ์ด ํ์ฅ ์์ด ๋ฒ ์ด์ค ๋ชจ๋ธ ๊ทธ๋๋ก ์ฌ์ฉ<br>
|
| 46 |
-๊ณ ๊ฐ ๋ฆฌ๋ทฐ๋ ์์
ํฌ์คํ
๊ณ ์ฐจ์ ๋ถ์ ๋ฐ ์ฝ๋ฉ๊ณผ ์๋ฌธ, ์ํ, ๋
ผ๋ฆฌํ๋จ ๋ฑ์ด ๊ฐํ๋ ๋ชจ๋ธ<br>
|
| 47 |
-128k-Context Window<br>
|
| 48 |
-
-Deepspeed Stage=3, rslora ๋ฐ BAdam Layer Mode ์ฌ์ฉ <br
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
Finetuned by Mr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics <br>
|
| 51 |
CPT(Continue-Pretraining)->SFT->DPO training model based on gemma-2-27b-it through 8 H100-80Gs as a Korean language model <br>
|
|
|
|
| 45 |
-ํ ํฌ๋์ด์ ๋ ๋จ์ด ํ์ฅ ์์ด ๋ฒ ์ด์ค ๋ชจ๋ธ ๊ทธ๋๋ก ์ฌ์ฉ<br>
|
| 46 |
-๊ณ ๊ฐ ๋ฆฌ๋ทฐ๋ ์์
ํฌ์คํ
๊ณ ์ฐจ์ ๋ถ์ ๋ฐ ์ฝ๋ฉ๊ณผ ์๋ฌธ, ์ํ, ๋
ผ๋ฆฌํ๋จ ๋ฑ์ด ๊ฐํ๋ ๋ชจ๋ธ<br>
|
| 47 |
-128k-Context Window<br>
|
| 48 |
+
-Deepspeed Stage=3, rslora ๋ฐ BAdam Layer Mode ์ฌ์ฉ <br>
|
| 49 |
+
-ollama run benedict/linkbricks-gemma2-27b-korean-advanced-q4 <br>
|
| 50 |
+
-ollama run benedict/linkbricks-gemma2-27b-korean-advanced-q8
|
| 51 |
+
<br><br>
|
| 52 |
|
| 53 |
Finetuned by Mr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics <br>
|
| 54 |
CPT(Continue-Pretraining)->SFT->DPO training model based on gemma-2-27b-it through 8 H100-80Gs as a Korean language model <br>
|