nvidia / usdcode-llama3-70b-instruct

Model Overview

Description:

USD Code (usdcode-llama3-70b-instruct) is an OpenUSD Python code generation and knowledge answering model that helps developers to write OpenUSD code and answer OpenUSD knowledge questions.

This model is available for preview, demonstration, and non-production usage on the NVIDIA API Catalog.

References:

Model Architecture:

Architecture Type: Transformer-Based Architecture

Network Architecture: Llama-3

Input

Input Type(s): Text

Input Format(s): String

Other Properties Related to Input: Max context length of 8k tokens

Output

Output Type(s): Text (Code, Python)

Output Format: String

Other Properties Related to Output: Max output length of 8k tokens

Software Integration:

Runtime Engine(s):

  • NIM 1.0.0

Supported Hardware Microarchitecture Compatibility:

  • NVIDIA Hopper

[Preferred/Supported] Operating System(s):

  • Linux

Model Version(s):

  • usdcode-llama3-70b-instruct-tuned-0703

Training, Testing, and Evaluation Datasets:

Training Dataset:

Data Collection Method by dataset

  • Hybrid: Automated, Synthetic

Labeling Method by dataset

  • Unknown

Properties (Quantity, Dataset Descriptions, Sensor(s)):

  • 59,729 question/answer pairs (text)

Testing Dataset:

Data Collection Method by dataset

  • Not Applicable

Labeling Method by dataset

  • Not Applicable

Properties (Quantity, Dataset Descriptions, Sensor(s)):

  • Not Applicable

Evaluation Dataset:

Data Collection Method by dataset

  • Hybrid: Automated, Synthetic

Labeling Method by dataset

  • Not Applicable

Properties (Quantity, Dataset Descriptions, Sensor(s)):

  • 100 question/answer pairs (text)

Inference:

Engine:

  • TensorRT

Test Hardware:

  • H100

Ethical Considerations (For NVIDIA Models Only):

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. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards.