NGC Catalog
CLASSIC
Welcome Guest
Resources
CodeGemma-7B-IT-INT4-RTX

CodeGemma-7B-IT-INT4-RTX

For downloads and more information, please view on a desktop device.
Description
CodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text decoder-only models. This is a 7 billion parameter instruction-tuned varient for code chat and instruction.
Publisher
Google
Latest Version
1.0
Modified
April 9, 2024
Compressed Size
6.22 GB

Model Overview

Description:

CodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text decoder-only models. This is a 7 billion parameter instruction-tuned varient for code chat and instruction.

Terms of use:

Use of this model is governed by the NVIDIA AI Foundation Models Community License. ADDITIONAL INFORMATION: Gemma Terms of Use and Google Prohibited Use Policy.

References(s):

  • CodeGemma Model Card

Model Architecture:

Architecture Type: Transformer

Input:

Input Format: Text

Input Parameters: None

Output:

Output Format: Text

Output Parameters: None

Software Integration:

Supported Hardware Platform(s): RTX 4090

Supported Operating System(s): Windows

Inference:

TRT-LLM Inference Engine
Windows Setup with TRT-LLM

Test Hardware:

RTX 4090