| --- |
| license: apache-2.0 |
| language: |
| - en |
| base_model: |
| - Qwen/Qwen3-0.6B |
| tags: |
| - multiturn |
| - toolcalling |
| - shellcommands |
| --- |
| |
| # Distil-Qwen3-0.6B-SHELLper |
|
|
| <p align="center"> |
| <img src="shellper.png" alt="SHELLper" width="200"> |
| </p> |
|
|
| A fine-tuned Qwen3-0.6B model for multi-turn bash function calling. Trained using knowledge distillation from Qwen3-235B, this 0.6B parameter model achieves 100% tool-call accuracy on our test set over multiple turns while being small enough to run locally on any machine. |
|
|
| ## Results |
| | Metric | Qwen3-235B (Teacher) | Qwen3-0.6B (Base) | This Model | |
| | --- | --- | --- | --- | |
| | Tool call accuracy | 99% | 84.16% | **100%** | |
| | 5-turn accuracy | 95% | 42.22% | **100%** | |
|
|
|
|
| ## Quick Start |
|
|
| You can follow instructions in our demo repository: [github](https://github.com/distil-labs/distil-SHELLper) |
|
|
| ### Using Ollama |
| ```bash |
| # Download and create Ollama model |
| hf download distil-labs/distil-qwen3-0.6b-SHELLper model_fp16.gguf Modelfile --local-dir distil_model |
| cd distil_model && ollama create distil_model -f Modelfile |
| cd .. |
| ``` |
|
|
| ### Using Transformers |
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model = AutoModelForCausalLM.from_pretrained("distil-labs/distil-qwen3-0.6b-SHELLper") |
| tokenizer = AutoTokenizer.from_pretrained("distil-labs/distil-qwen3-0.6b-SHELLper") |
| |
| tools = [ |
| { |
| "type": "function", |
| "function": { |
| "name": "ls", |
| "description": "List directory contents", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "folder": {"type": "string", "description": "Path to the folder to list"} |
| }, |
| "required": ["folder"] |
| } |
| } |
| } |
| ] |
| |
| messages = [ |
| {"role": "system", "content": "You are a helpful assistant that executes bash commands."}, |
| {"role": "user", "content": "List all files in the current directory"} |
| ] |
| |
| text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True) |
| inputs = tokenizer(text, return_tensors="pt") |
| outputs = model.generate(**inputs, max_new_tokens=256, temperature=0) |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
| ``` |
|
|
| ## Model Details |
| | Property | Value | |
| | --- | --- | |
| | Base Model | Qwen/Qwen3-0.6B | |
| | Parameters | 0.6 billion | |
| | Architecture | Qwen3ForCausalLM | |
| | Context Length | 40,960 tokens | |
| | Precision | bfloat16 | |
| | Training Data | ~200 synthetic examples (expanded from 20 seeds) | |
| | Teacher Model | Qwen3-235B-A22B-Instruct | |
|
|
| ## Training |
| This model was trained using the Distil Labs platform: |
|
|
| - **Seed Data:** 20 hand-validated multi-turn bash command conversations |
| - **Synthetic Generation:** Expanded using Qwen3-235B teacher with conversation turn expansion |
| - **Fine-tuning:** 4 epochs with LoRA (r=128) on the synthetic dataset |
| - **Evaluation:** Multi-turn accuracy testing across variable conversation lengths |
|
|
| ### Training Hyperparameters |
| - Epochs: 4 |
| - Learning Rate: 2e-5 (linear schedule) |
| - Batch Size: 1 (with gradient accumulation) |
| - LoRA Rank: 128 |
|
|
| ## Task Format |
|
|
| ### Input Format |
| Multi-turn conversation with tool definitions: |
| ```json |
| [ |
| {"role": "user", "content": "List all files in the current directory"}, |
| {"role": "assistant", "tool_calls": [{"function": {"name": "ls", "arguments": {"folder": "."}}}]}, |
| {"role": "user", "content": "Now go to the src folder"} |
| ] |
| ``` |
|
|
| ### Output Format |
| A single tool call in JSON format: |
| ```json |
| {"name": "cd", "arguments": {"folder": "src"}} |
| ``` |
|
|
| ## Supported Tools |
| The model supports 20 bash commands: |
|
|
| | Command | Description | |
| | --- | --- | |
| | `cat` | Display file contents | |
| | `cd` | Change directory | |
| | `cp` | Copy files or directories | |
| | `diff` | Compare files | |
| | `du` | Estimate file space usage | |
| | `echo` | Display text | |
| | `find` | Search for files | |
| | `grep` | Search file contents | |
| | `head` | Output first part of files | |
| | `ls` | List directory contents | |
| | `mkdir` | Create directories | |
| | `mv` | Move or rename files | |
| | `pwd` | Print working directory | |
| | `rm` | Remove files | |
| | `rmdir` | Remove empty directories | |
| | `sort` | Sort file contents | |
| | `tail` | Output last part of files | |
| | `touch` | Create empty files | |
| | `wc` | Word, line, character count | |
|
|
| ## Use Cases |
| - Natural language interfaces to file systems |
| - Command-line assistants and automation |
| - Developer productivity tools |
| - Educational tools for learning bash |
| - Local, privacy-preserving AI assistants |
|
|
| ## Limitations |
| - Optimized for single tool call per turn |
| - No support for pipes or combined commands |
| - Best with up to 5 conversation turns |
| - Trained on English requests only |
| - Limited to the 20 supported bash commands |
|
|
| ## License |
| This model is released under the Apache 2.0 license. |
|
|
| ## Links |
| - [Distil Labs Website](https://www.distillabs.ai/?utm_source=huggingface&utm_medium=referral&utm_campaign=shellper) |
| - [GitHub](https://github.com/distil-labs) |
| - [Hugging Face](https://huggingface.co/distil-labs) |
|
|
| ## Citation |
| ```bibtex |
| @misc{distil-qwen3-0.6b-shellper, |
| author = {Distil Labs}, |
| title = {Distil-Qwen3-0.6B-SHELLper: A Fine-tuned Model for Multi-turn Bash Function Calling}, |
| year = {2025}, |
| publisher = {Hugging Face}, |
| url = {https://huggingface.co/distil-labs/distil-qwen3-0.6b-SHELLper} |
| } |
| ``` |
|
|
