Qwen3-0.6B-Sushi-Math-Code-Expert

qwen3-sushi-math-code-expert/
├── main.py               # Core Python script for model loading, inference pipeline, and query handling
├── requirements.txt      # Dependencies for correct implementation
├── config.yaml           # Configuration for model, device, and pipeline settings
├── prompts.json          # JSON file for predefined prompt templates (e.g., thinking mode)
├── logs/                 # Folder for runtime logs (created dynamically)
│   └── inference.log     # TXT log file (appended during runtime)
└── db/                   # Folder for simple SQLite DB for query history
    └── history.db        # SQLite DB file (created dynamically)

model:
  name: "gss1147/Qwen3-0.6B-Sushi-Math-Code-Expert"
  dtype: "float16"
  trust_remote_code: true

pipeline:
  max_length: 512
  temperature: 0.7
  top_p: 0.9
  thinking_mode: true  # Enable thinking mode for math/code reasoning

device:
  type: "cuda"  # Use "cpu" if no GPU

logging:
  log_file: "logs/inference.log"
  db_file: "db/history.db"

{
  "thinking_mode": "You are a math and code expert. Use /think to enable thinking mode for complex reasoning. Query: {query}",
  "non_thinking_mode": "You are a general assistant. Use /no_think for efficient response. Query: {query}"
}