Mistral-Nemo-12B-Instruct-ONNX-INT4

Model Developer : Mistral

Model Description

Mistral-NeMo is a Large Language Model (LLM) composed of 12B parameters. This model leads accuracy on popular benchmarks across common sense reasoning, coding, math, multilingual and multi-turn chat tasks; it significantly outperforms existing models smaller or similar in size.   The NVIDIA Mistral-Nemo-12B Instruct ONNX INT4 model is quantized with TensorRT Model Optimizer.

Steps followed to generate this quantized model:

• 1. Download Mistral-Nemo-12B Instruct model in Pytorch bfloat16 format from HuggingFace.
• 2. Convert PyTorch model to ONNX FP16 using onnxruntime-genai model builder.
• 3. Quantize Mistral-Nemo-12B Instruct ONNX FP16 model to Mistral-Nemo-12B Instruct ONNX INT4 AWQ model using TensorRT Model Optimizer – Windows.

This model is ready for commercial/non-commercial use. 

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 Non-NVIDIA Mistral-Nemo-12B-Instruct Model Card

License/Terms of Use:

GOVERNING TERMS: Use of this model is governed by the NVIDIA Open Model License Agreement (found at https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf ). ADDITIONAL INFORMATION: Apache License, Version 2.0 (found at https://huggingface.co./datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md ).

Reference(s):

Mistral NeMo 12B Blogpost

Model Architecture:

Mistral NeMo, a 12B model built in collaboration with NVIDIA. Mistral NeMo offers a large context window of up to 128k tokens. Its reasoning, world knowledge, and coding accuracy are state-of-the-art in its size category. As it relies on standard architecture, Mistral NeMo is easy to use as a drop-in replacement in any system using Mistral 7B. 

Architecture Type: Transformer

Network Architecture: Mistral

Input

• Input Type: Text

• Input Format: String

• Input Parameters: 1D

• Other Properties Related to Input: max_tokens, temperature, top_p, stop, frequency_penalty, presence_penalty, seed

Output

• Output Type: Text

• Output Format: String

• Output Parameters: 1D

Software Integration:

• Supported Hardware Platform(s):  Nvidia Ampere and newer GPUs. 6GB or higher VRAM GPUs are recommended. Higher VRAM may be required for larger context length use cases. 

• Supported Operating System(s):  Windows

 

Model Version(s):  1.0

Training, Testing, and Evaluation Datasets:

Refer to Mistral-Nemo-12B-Instruct Model Card for the details. 

Evaluation Dataset:

Link: https://people.eecs.berkeley.edu/~hendrycks/data.tar

• Data Collection Method by dataset  - Unknown

• Labeling Method by dataset  - Not Applicable

Evaluation Results:

MMLU (5# shots):

With GenAI ORT->DML backend, we got below accuracy numbers on a desktop RTX 4090 GPU system. 

"overall_accuracy": 66.74

Test configuration:

• GPU: RTX 4090.  

• Windows 11: 23H2

• NVIDIA Graphics driver: R565 or higher

Inference:

We used GenAI ORT->DML backend for inference. The instructions to use this backend are given in readme.txt file available under Files section. 

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.