初始化项目,由ModelHub XC社区提供模型
Model: hyunseoki/ko-en-llama2-13b Source: Original Platform
This commit is contained in:
25
README.md
Normal file
25
README.md
Normal file
@@ -0,0 +1,25 @@
|
||||
---
|
||||
language:
|
||||
- ko
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
**Model Developers** HyunseokLee, TaeyoungKim - (kaist alinlab, omnious.ai)
|
||||
|
||||
**Input** Models input text only.
|
||||
|
||||
**Output** Models generate text only.
|
||||
|
||||
**Model Architecture**
|
||||
ko-en-llama2-13b is an auto-regressive language model based on the LLaMA2 transformer architecture.
|
||||
|
||||
**Base Model**
|
||||
Llama-2-13B
|
||||
|
||||
**Training Dataset**
|
||||
Open dataset wiki and AIhub (English + Korean).
|
||||
|
||||
**Training Objective**
|
||||
We trained the model to learn Korean corpus while maintaining Llama's English ability.
|
||||
(still training)
|
||||
Reference in New Issue
Block a user