matsuo-llm-advanced-phase-b

Qwen2.5-7B-Instruct Fine-tuned (Phase B)

Fine-tuned version of Qwen/Qwen2.5-7B-Instruct for agent task performance (ALFWorld + DBBench).

Training Data

• u-10bei/dbbench_sft_dataset_react_v4 — Listed in the organizer-shared Phase B dataset list. Used as provided (no modification). Third-party synthetic SFT for DBBench format alignment; all tables, data, and queries are independently generated (per dataset description: "to avoid test data leakage").
• xlangai/spider — CC BY-SA 4.0 (Yale/Columbia Spider project)
• birdsql/bird_mini_dev — CC BY-SA 4.0 (HKU)

Compliance

• Base model: Qwen2.5-7B-Instruct (Apache 2.0 license)
• No inference code modification
• No RAG/ToolUse
• No commercial API usage
• Evaluation data not used in training: No analysis of evaluation test data was conducted. Training data was selected solely from the public datasets listed above.
• LLM was not used for data quality filtering or selection.

Usage

python -m vllm.entrypoints.openai.api_server \
    --model astom-M/matsuo-llm-advanced-phase-b \
    --dtype bfloat16 \
    --max-model-len 8192

License

Apache 2.0 (inherited from Qwen2.5-7B-Instruct)