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
Updated 7 min ago
Stars gained each day, last 30 days
Oct 9Oct 24
This week Before
In short
Adds the requirements the description skips: training runs on a free Kaggle T4 GPU, while inference is meant for a local 8 GB Apple Silicon Mac via GGUF and llama.cpp. The code executes to verify answers rather than relying on the model's memory.
Summary written by AI from the repository’s description and README.
pnnnx / local-code-tutor
View on GitHub(opens in new tab)