metadata
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:
- korean
- text
model-index:
- name: Vere1Ko-0.6B
results: []
datasets:
- MarkrAI/KoCommercial-Dataset
1. Vere Series
The Vere series has the following characteristics:
- Small Size: The model itself is small, allowing it to run in various environments.
- Focus on a Single Field: As a small model, it is difficult to excel in all areas. Therefore, it is trained to specialize in a specific field rather than being a generalist.
- Variety of Models: Since it doesn't cover all fields, many specialized models are released for each area (with more diverse models planned for the future).
2. VereKo Series
VereKo has the following characteristics:
- Korean Specialization: It has been trained on a large amount of Korean data, making it proficient in the Korean language.
3. About This Model
- Model Name: Vere1Ko-0.6B
- Base Model: Qwen/Qwen3-0.6B
- Fine-tuning Dataset: MarkrAI/KoCommercial-Dataset
- Computational Power: Combining Qwen3-0.6B's performance with KoCommercial-Dataset delivers enhanced computational capabilities.
- Korean Specialized: Fine-tuned on the KoCommercial-Dataset, providing strong proficiency in Korean.
- Max Tokens: Inherits Qwen3-0.6B's large maximum token limit, enabling effective processing of long texts.
4. Reason for Creation
I created this model because I wanted a Korean-proficient model with a small parameter size that can run smoothly across various environments.