Skip to content

README.md

Latest commit

 

History

History
81 lines (55 loc) · 3.13 KB

README.md

File metadata and controls

81 lines (55 loc) · 3.13 KB

Gemma 2 27b it

📖 Introduction

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

Task Type Description
Chat A task to generate conversational style text output base on single or multi-modality input.

🔄 Compatibility Matrix

To ensure smooth integration, please refer to the compatibility matrix below. It outlines the compatible versions of the model, instill-core, and the python-sdk.

Instill Core Version Python SDK Version
>= v0.51.0 >= v0.18.0

Note: Always ensure that you are using compatible versions to avoid unexpected issues.

🚀 Preparation

Follow this guide to get your custom model up and running! But before you do that, please read through the following sections to have all the necessary files ready.

Install Python SDK

Install the compatible python-sdk version according to the compatibility matrix:

pip install instill-sdk=={version}

Get model weights

To download the fine-tuned model weights, please execute the following command:

git clone https://huggingface.co/google/gemma-2-27b-it

Test model image

After you've built the model image, and before pushing the model onto any Instill Core instance, you can test if the model can be successfully run locally first, by running the following command:

instill run admin/gemma2 -g -i '{"prompt": "hows life?"}'

The input payload should strictly follow the the below format

{
  "prompt": "..."
}

A successful response will return a similar output to that shown below.

2024-11-28 21:15:42,947.947 INFO     [Instill] Starting model image...
2024-11-28 21:15:58,526.526 INFO     [Instill] Deploying model...
2024-11-28 21:23:34,019.019 INFO     [Instill] Running inference...
2024-11-28 21:24:24,381.381 INFO     [Instill] Outputs:
[{'data': {'choices': [{'created': 1732800261,
                        'finish-reason': 'length',
                        'index': 0,
                        'message': {'content': "As an AI, I don't experience "
                                               'life in the same way humans do',
                                    'role': 'assistant'}}]}}]
2024-11-28 21:24:45,672.672 INFO     [Instill] Done

Here is the list of flags supported by instill run command

  • -t, --tag: tag for the model image, default to latest
  • -g, --gpu: to pass through GPU from host into container or not, depends on if gpu is enabled in the config.
  • -i, --input: input in json format

Happy Modeling! 💡