GitHub · Python
pnnnx/local-code-tutor
Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, llama.cpp, LoRA weight analysis with charts
- Stars
- 15
- Forks
- 0
- Stars gained in 24 hours
- Not enough history yet
- Forks gained in 24 hours
- Not enough history yet
Topics: ai-agent, apple-silicon, coding-assistant, dataset-generation, fine-tuning, gguf, interpretability, kaggle, llama-cpp, llm
Latest data point: Nov 22, 2026 · 15 stars · 0 forks