Image-Text-to-Text
Transformers
Safetensors
gemma3n
automatic-speech-recognition
automatic-speech-translation
audio-text-to-text
video-text-to-text
Instructions to use google/gemma-3n-E4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-3n-E4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="google/gemma-3n-E4B")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/gemma-3n-E4B") model = AutoModelForImageTextToText.from_pretrained("google/gemma-3n-E4B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/gemma-3n-E4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/gemma-3n-E4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/gemma-3n-E4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/gemma-3n-E4B
- SGLang
How to use google/gemma-3n-E4B 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/gemma-3n-E4B" \ --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/gemma-3n-E4B", "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/gemma-3n-E4B" \ --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/gemma-3n-E4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/gemma-3n-E4B with Docker Model Runner:
docker model run hf.co/google/gemma-3n-E4B
video input with gemma 3n
#7
by himasai9711 - opened
Hi @himasai9711 ,
If you would like to provided the image as an input to the model you could directly provide it in the prompt by using the chat template provided in the model card section, however if you would like to do the video analysis you have to pass the frames as an input to the model in an iterative manner to analyze it .
To know more about how to do the video analysis with Gemma models kindly refer this page. if you have any concerns let us know will assist you.
Thank you.