Model Overview

Description:

Model developer: Meta

Meta Llama 3.1 8B Instruct INT4 ONNX

Built with Meta - Llama 3.1 8B Instruct INT4 ONNX model is the AWQ quantized version of the Meta Llama-3.1-8B-Instruct model, which is an auto-regressive language model that uses an optimized transformer architecture for multilingual dialogue use cases. For more information, please check here. The Llama 3.1 8B Instruct INT4 ONNX model is quantized with TensorRT Model Optimizer.

This model is ready for commercial and research use case.

Steps followed to generate this quantized model:

• Download Meta Llama-3.1-8B-Instruct model in Pytorch bfloat16 format from HuggingFace.

• Convert PyTorch model to ONNX FP16 using onnxruntime-genai model builder.

• Quantize Llama-3.1-8B-Instruct ONNX FP16 model to Llama-3.1-8B ONNX INT4 AWQ model using TensorRT Model Optimizer – Windows.

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; see link to the non-NVIDIA Meta-Llama-3.1-Instruct Model Card.

License/Terms of Use:

Governing Terms: Use of this model is governed by the NVIDIA Open Model License Agreement. Additional Information: Llama 3.1 Community License Agreement, Built with Llama.

References:

• Meta Llama 3.1 Model Card on Hugging face

• The Llama 3 Herd of Models

• Meta Llama 3 blogpost

Model Architecture:

Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

Architecture Type: Transformer

Network Architecture: Llama 3.1

Input:

Input Type: Text

Input Format: String

Input Parameters: Sequences (1D)

Other Properties Related to Input: Supports English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai

Output:

Output Type(s): Text

Output Format: String

Output Parameters: Sequence (1D)

Software Integration:

Supported Hardware Microarchitecture Compatibility: NVIDIA Ampere and newer GPUs. 6GB or higher GPU video memory are recommended. Higher VRAM may be required for larger context length use cases.

Supported Operating System: Windows

Model Version: v1.0

Training, Testing, and Evaluation Datasets:

Refer to Llama 3.1 Model Card for the details.

Training Dataset: cnn_dailymail used for calibration.

• Link: cnn_dailymail

• Data Collection Method by dataset: [Automated]

• Labeling Method by dataset: [Unknown]

Evaluation Dataset: MMLU

• Link:MMLU

• Data Collection Method by dataset: [Unknown]

• Labeling Method by dataset: [Not Applicable]

Evaluation Results:

Accuracy Scores: MMLU (5 shots):

With GenAI ORT->DML backend, on a desktop RTX 4090 GPU system.

“Overall accuracy” = 66.1

Test configuration:

• GPU: RTX 4090, RTX 3090.  

• Windows 11: 23H2

• NVIDIA Graphics driver: R565 or higher

Inference:

Inference Backend: Onnxruntime-GenAI-DirectML

(Note: Please refer to Readme.txt for the detailed instructions.)

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.