Instructions to use google/vaultgemma-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/vaultgemma-1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="google/vaultgemma-1b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/vaultgemma-1b") model = AutoModelForCausalLM.from_pretrained("google/vaultgemma-1b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use google/vaultgemma-1b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/vaultgemma-1b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/vaultgemma-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/vaultgemma-1b
- SGLang
How to use google/vaultgemma-1b 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/vaultgemma-1b" \ --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/vaultgemma-1b", "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/vaultgemma-1b" \ --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/vaultgemma-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/vaultgemma-1b with Docker Model Runner:
docker model run hf.co/google/vaultgemma-1b
Unable to run on Collab
I tried to run vaultgemma on Google Colab, but I see the following error.
ValueError: The checkpoint you are trying to load has model type vaultgemma but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
Am I missing something?
Thanks for your interest in the model! Support for VaultGemma was added to Transformers in a special release on top of v4.56.1, and will be present in v4.57.0 when that version is released.
In the meantime, you can use this command in Colab to install the special release of the library: pip install git+https://github.com/huggingface/transformers@v4.56.1-Vault-Gemma-preview
For more information, check the release notes for that version on GitHub: https://github.com/huggingface/transformers/releases/tag/v4.56.1-Vault-Gemma-preview
Hi @samairtimer ,
Could you please confirm if you tried with the latest transformers version and the command from previous comments. if you have any concerns , please let us know, and we will be happy to assist on this.
Thank you.
It worked! Thank you/
Could you have a look at https://huggingface.co/google/vaultgemma-1b/discussions/6