Update README.md
Browse files
README.md
CHANGED
@@ -10,14 +10,14 @@ language:
|
|
10 |
* K2S3
|
11 |
|
12 |
## Model Number:
|
13 |
-
* K2S3-14b-v0.
|
14 |
|
15 |
## Base Model Weight :
|
16 |
* mistralai/Mistral-7B-v0.1
|
17 |
|
18 |
## Model Description :
|
19 |
-
* The K2S3 v0.
|
20 |
-
* K2S3 v0.
|
21 |
|
22 |
### Training Data
|
23 |
* The training data for this model includes alpaca-gpt4-data, and samples from The OpenOrca Dataset.
|
|
|
10 |
* K2S3
|
11 |
|
12 |
## Model Number:
|
13 |
+
* K2S3-14b-v0.2
|
14 |
|
15 |
## Base Model Weight :
|
16 |
* mistralai/Mistral-7B-v0.1
|
17 |
|
18 |
## Model Description :
|
19 |
+
* The K2S3 v0.2 model utilizes mistral weights, having undergone depth up scaling to double its size, and has been enhanced with the addition of Korean vocabulary and merges to the tokenizer.
|
20 |
+
* K2S3 v0.2 모델은 mistral weight를 활용하였으며, depth up scaling을 통해 모델의 크기를 2배로 확장하였습니다. 또한, 토크나이저에는 한글 vocab과 merges를 추가하여 한국어 처리 능력을 강화하였습니다.
|
21 |
|
22 |
### Training Data
|
23 |
* The training data for this model includes alpaca-gpt4-data, and samples from The OpenOrca Dataset.
|