GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
distil-labs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
distil-labs
Model Tree
google/gemma-3-270m-it
Input Modalities
Output Modalities
Supported Functionality
| Metric | GPT OSS 120B (Teacher) | Gemma 3 270M (Base) | This Model |
|---|---|---|---|
| Tool call accuracy | 97.03% | 9.90% | 96.04% |
| ROUGE-L | 94.42% | 49.73% | 96.55% |
You can follow instructions in our demo repository: github
bash
# Download and create Ollama modelhuggingface-cli download distil-labs/distil-gemma3-270m-SHELLper model.gguf Modelfile --local-dir distil_modelcd distil_model && ollama create distil_model -f Modelfilecd ..python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("distil-labs/distil-gemma3-270m-SHELLper")tokenizer = AutoTokenizer.from_pretrained("distil-labs/distil-gemma3-270m-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))| Property | Value |
|---|---|
| Base Model | google/gemma-3-270m-it |
| Parameters | 270 million |
| Architecture | Gemma3ForCausalLM |
| Context Length | 32,768 tokens |
| Precision | bfloat16 |
| Training Data | ~10,000 synthetic examples (expanded from 20 seeds) |
| Teacher Model | GPT OSS 120B |
This model was trained using the Distil Labs platform:
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"}]A single tool call in JSON format:
json
{"name": "cd", "arguments": {"folder": "src"}}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 |
This model is released under the Apache 2.0 license.
bibtex
@misc{distil-gemma3-270m-shellper, author = {Distil Labs}, title = {Distil-Gemma3-270M-SHELLper: A Fine-tuned Model for Multi-turn Bash Function Calling}, year = {2025}, publisher = {Hugging Face}, url = {https://huggingface.co/distil-labs/distil-gemma3-270m-SHELLper}}# Download and create Ollama modelhuggingface-cli download distil-labs/distil-gemma3-270m-SHELLper model.gguf Modelfile --local-dir distil_modelcd distil_model && ollama create distil_model -f Modelfilecd ..from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("distil-labs/distil-gemma3-270m-SHELLper")tokenizer = AutoTokenizer.from_pretrained("distil-labs/distil-gemma3-270m-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))[ {"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"}]{"name": "cd", "arguments": {"folder": "src"}}@misc{distil-gemma3-270m-shellper, author = {Distil Labs}, title = {Distil-Gemma3-270M-SHELLper: A Fine-tuned Model for Multi-turn Bash Function Calling}, year = {2025}, publisher = {Hugging Face}, url = {https://huggingface.co/distil-labs/distil-gemma3-270m-SHELLper}}