Downloads · 30 days
34
28% of all-time downloads
seongwonkim/AIWORKX-KR-KG-Reasoner-0.5B-v0.10
AIWORKX-KR-KG-Reasoner-0.5B-v0.10 is a text generation model from seongwonkim. Use it when you need the model to write or continue text. The card lists the license as other.
AIWORKX-KR-KG-Reasoner-0.5B-v0.10 is a small Korean-specialized language model fine-tuned from Qwen/Qwen2.5-0.5B-Instruct.
Downloads · 30 days
34
28% of all-time downloads
All-time downloads
122
Public
Parameters
494M
1000 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors988 MB · 99%
From the Hugging Face model README
AIWORKX-KR-KG-Reasoner-0.5B-v0.10 is a small Korean-specialized language model fine-tuned from Qwen/Qwen2.5-0.5B-Instruct.
This model was created as a local MVP for K-AI leaderboard submission experiments. The training pipeline uses copyright-safe structured factual triples, converts them into a local knowledge graph, and generates Korean supervised fine-tuning data through deterministic rule-based templates.
Qwen/Qwen2.5-0.5B-InstructThe training data was generated from local structured factual triples.
Pipeline:
No OpenAI API, paid API, live external API, or web crawling was used in this MVP.
The dataset uses structured factual triples rather than copied prose. The project is designed around copyright-safe factual data and knowledge-graph-based training.
This is a small experimental model trained on a very small dataset. It may overfit to the rule-based format and may not perform well on broad open-domain tasks. It should not be used for high-stakes decisions.