Roadmap

Current pipeline status for Code-Trainer V6.

# Phase Status Tech
01 Data Collection ✓ Complete Playwright, GitPython, …
02 Preprocessing ✓ Complete HuggingFace Datasets, Pillow, …
03 Vision Model ● Ready PyTorch, Transformers, …
04 Qwen Fine-tuning ● Ready HF Skills API, PEFT LoRA, …
05 GGUF Deployment ● Ready llama.cpp, GGUF Q4_K_M, …
06 Inference Agent ○ Planned vLLM, Qwen-Agent, …

Model

  • Base model: Qwen2.5-Coder-14B-Instruct
  • Hardware: RTX 5060 Ti 16GB (Blackwell)
  • HF Dataset: cmndcntrlcyber/code-trainer-v6-dataset
  • HF Model: cmndcntrlcyber/qwen14b-code-trainer-v6