Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha

Qwen2.5-1.5B SFT (Practice Model)

This is a practice / for-learning-only model based on Qwen/Qwen2.5-1.5B, fine-tuned with Supervised Fine-Tuning (SFT) as a personal study exercise.

What this is

• Base model: Qwen/Qwen2.5-1.5B
• Training method: SFT (Supervised Fine-Tuning)
• Purpose: educational / practice only — not intended for production use
• Expect poor or inconsistent outputs; this checkpoint exists to learn the SFT pipeline, not to be a useful assistant

Intended use

• Studying how SFT changes a small base model
• Comparing SFT vs. base model behavior
• Experimenting with training data, hyperparameters, and merges

Do not use this model for any real-world task or deployment.

License

Apache 2.0, inherited from the base Qwen2.5 model. See the Qwen2.5 license for details.