NGC Catalog
CLASSIC
Welcome Guest
Models
Gemma 2B Instruct (TensorRT LLM)

Gemma 2B Instruct (TensorRT LLM)

For downloads and more information, please view on a desktop device.
Logo for Gemma 2B Instruct (TensorRT LLM)
Description
Gemma-2B is a 2.5B parameter model from Gemma family of models from Google. It has been instruction-tuned so it can respond to prompts in a conversational manner.
Publisher
NVIDIA
Latest Version
bs1_int8wo_RTX4090_windows
Modified
June 14, 2024
Size
2.4 GB

Model Overview

Terms of use:

GOVERNING TERMS: By accessing this engine, you are agreeing to NVIDIA TensorRT Engine License.

ATTRIBUTION: Gemma Terms of Use available at https://ai.google.dev/gemma/terms; and Gemma Prohibited Use Policy available at https://ai.google.dev/gemma/prohibited_use_policy.

Third-Party Community Consideration

This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case. 

Description:

Gemma-2B is a 2.5B parameter model from Gemma family of models from Google. It has been instruction-tuned so it can respond to prompts in a conversational manner. Nvidia has converted original Gemma weights and format into weights and format that can be consumed by TensorRT-LLM. TensorRT engines optimizing Gemma-2B are generated by TensorRT-Cloud. 

These TensorRT engines are ready for commercial use.    

References(s):

  • Gemma Model Card 
  • Gemma blogpost 

Input:

Input Format: Text
Input Parameters: None   

Output:

Output Format: Text 
Output Parameters: None 

Software Integration:

Check the version tag for engine support matrix  

Inference:

TRT-LLM Inference Engine

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns here.