thuethainguyen/agent

Distil-Qwen3-0.6B-SHELLper

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

Using Ollama

# 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

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:

[
  {"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:

{"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
• GitHub
• Hugging Face

Citation

@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}
}