kawatoshi3/exp2a-lora

HyperParam Tuning LoRA (max_seq_len=2048)

LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth).

Training Configuration

• Base model: Qwen/Qwen3-4B-Instruct-2507
• Dataset: u-10bei/structured_data_with_cot_dataset_v2
• Method: QLoRA (4-bit)
• Max sequence length: 2048
• Epochs: 3
• Learning rate: 0.0001
• LoRA: r=64, alpha=128

Sources & License

• Training Data: u-10bei/structured_data_with_cot_dataset_v2
• Dataset License: CC-BY-4.0. This dataset is used and can be redistributed under the terms of the CC-BY-4.0 license.
• Compliance: Users must comply with both the dataset attribution requirements and the base model original terms of use.