Instructions to use google/functiongemma-270m-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/functiongemma-270m-it with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="google/functiongemma-270m-it")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/functiongemma-270m-it", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/functiongemma-270m-it with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/functiongemma-270m-it" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/functiongemma-270m-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/functiongemma-270m-it
- SGLang
How to use google/functiongemma-270m-it with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "google/functiongemma-270m-it" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/functiongemma-270m-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "google/functiongemma-270m-it" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/functiongemma-270m-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/functiongemma-270m-it with Docker Model Runner:
docker model run hf.co/google/functiongemma-270m-it
Fixing MLX stop tokens
#3
by prince-canuma - opened
No description provided.
We need to change the stop token to be 1 and 50 (not 49)
Out of curiosity, I Tested with both configurations:
eos_token_id: [1, 49] (stops at <end_function_call>)
- Generates only the first tool call, ignores subsequent requests
- Example: "Get weather AND calculate 15*23" → only weather call generated
eos_token_id: [1, 50] (stops at <start_function_response>)
- Generates all tool calls before stopping
- Example: same prompt → both weather and calculate calls generated
Token 50 enables multi-tool calling. [1, 50] seems like better choice.