Qwen2.5-Coder-1.5B CLI
Experimental Linux Command Generator
1 min read
This model was trained using Supervised Fine-Tuning (SFT) with LoRA (a small adapter built on top of the base model) based on Qwen2.5-Coder-1.5B-Instruct. It turns natural language text prompts into Linux command-line instructions. The project was created as an experimental step toward a full-fledged system administration assistant. The model is delivered in GGUF format with Q4_K_M quantization, making it convenient for local execution.
Key features
- Base: Qwen2.5-Coder-1.5B-Instruct
- Training method: Supervised Fine-Tuning (SFT) with LoRA
- Training data: 40,634 examples
- Format: GGUF (Q4_K_M)
What you can do
- Generate Linux shell commands from a text description of a task
- Use it for assistance with basic system administration
- Test the model capabilities locally for working with the console
Example
Prompt: "Find all files modified in the last 7 days and delete them"
Result: Generation of the corresponding file search and deletion command in the Linux terminal.
Read more
DetailsAccuracy (exact-match accuracy): baseline 11% → fine-tuned 18% (+7 percentage points)
Final training loss: 0.7867
Trainable parameters: 36.93M (2.34%)
Limitations: Experimental version, commands require verification before execution










Comments