Downloads · 30 days
837
2% of all-time downloads
ko-wand-136M
instructkr/ko-wand-136M
ko-wand-136M is a text generation model from instructkr. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
ko-wand-136M는 insturctkr에서 사전학습한 SLM입니다.
All-time downloads
39.7K
Public
Repo size
743 MB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin371 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Jan 1, 2024
- Updated
- Jan 1, 2024
- SHA
- 86cc9bf2
Model card
From the Hugging Face model README
ko-wand-136M
ko-wand-136M는 insturctkr에서 사전학습한 SLM입니다.
Model Description
maywell/korean_textbooks와 한국어 말뭉치를 이용하여 사전학습 되었습니다.
Model Info
미스트랄 아키텍쳐를 기반으로 완전히 랜덤 가중치를 시작으로 사전학습 된 모델입니다. Instruction 튜닝되지 않았습니다.
Training Details
| Batch Size | Token Seen | lr |
|---|---|---|
| 1024 | 2.5B | 2e-3 (cosine) |
License
apache-2.0
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Languages
- ko, en
- Created
- Jan 1, 2024
- Updated
- Jan 1, 2024