nl2shell-0.8b / README.md
AryaYT's picture
Upload README.md with huggingface_hub
752730f verified
---
license: mit
base_model: Qwen/Qwen3.5-0.8B
tags:
- nl2bash
- shell
- terminal
- command-line
- qwen3.5
- qlora
- cloudagi
datasets:
- GWHed/nl2bash
language:
- en
pipeline_tag: text-generation
---
# NL2Shell 0.8B — Natural Language to Shell Commands
Fine-tuned [Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) for converting natural language to shell commands.
## Quick Start
```bash
ollama run hf.co/AryaYT/nl2shell-0.8b
```
## Training
- **Method:** QLoRA (r=16, alpha=32, 4-bit NF4, all linear layers)
- **Data:** [NL2Bash](https://huggingface.co/datasets/GWHed/nl2bash) (8,130 pairs) + 40 macOS synthetic
- **Epochs:** 3 | **Loss:** 0.6338 | **Hardware:** A100 40GB
- **Architecture:** Hybrid DeltaNet (75% linear + 25% softmax attention)
## Prompt Format (ChatML)
```
<|im_start|>system
You are an expert shell programmer. Given a natural language request, output ONLY the corresponding shell command. No explanations.<|im_end|>
<|im_start|>user
find all Python files modified today<|im_end|>
<|im_start|>assistant
```
## License
MIT | Built by [Arya Teja](https://github.com/aryateja2106) | [CloudAGI](https://cloudagi.ai)