EmbeddedLLM/openchat-3.6-8b-20240522-onnx
By EmbeddedLLM · ↓ 0 · ♥ 1 · Updated 2024-06-17
What's in this repo
This page lists the files in EmbeddedLLM/openchat-3.6-8b-20240522-onnx, including model.onnx and more.
- 3 ONNX models (.onnx files)
- 23 files, including 15 .json, 3 .onnx, 3 .data, 1 .md
- Last updated 2024-06-17
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/model.onnx | — | Download |
| onnx/cpu_and_mobile/cpu-int4-rtn-block-32/model.onnx | — | Download |
| onnx/directml/openchat-3.6-8b-20240522-int4/model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
openchat-3.6-8b-20240522 ONNX
Model Summary
This repository contains the ONNX-optimized version of openchat/openchat-3.6-8b-20240522, designed to accelerate inference using ONNX Runtime. These optimizations are specifically tailored for CPU and DirectML. DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning, offering GPU acceleration across a wide range of supported hardware and drivers, including those from AMD, Intel, NVIDIA, and Qualcomm.
Optimized Configurations
The following optimized configurations are available:
- ONNX model for int4 DirectML: Optimized for AMD, Intel, and NVIDIA GPUs on Windows, quantized to int4 using AWQ.
- ONNX model for int4 CPU and Mobile: ONNX model for CPU and mobile using int4 quantization via RTN. There are two versions uploaded to balance latency vs. accuracy. Acc=1 is targeted at improved accuracy, while Acc=4 is for improved performance. For mobile devices, we recommend using the model with acc-level-4.
Usage
Installation and Setup
To use the EmbeddedLLM/openchat-3.6-8b-20240522-onnx model on Windows with DirectML, follow these steps:
- Create and activate a Conda environment:
conda create -n onnx python=3.10
conda activate onnx
- Install Git LFS:
winget install -e --id GitHub.GitLFS
- Install Hugging Face CLI:
pip install huggingface-hub[cli]
- Download the model:
huggingface-cli download EmbeddedLLM/openchat-3.6-8b-20240522-onnx --include="onnx/directml/*" --local-dir .\openchat-3.6-8b-20240522-onnx
- Install necessary Python packages:
pip install numpy==1.26.4
pip install onnxruntime-directml
pip install --pre onnxruntime-genai-directml
- Install Visual Studio 2015 runtime:
conda install conda-forge::vs2015_runtime
- Download the example script:
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/phi3-qa.py" -OutFile "phi3-qa.py"
- Run the example script:
python phi3-qa.py -m .\openchat-3.6-8b-20240522-onnx
Hardware Requirements
Minimum Configuration:
- Windows: DirectX 12-capable GPU (AMD/Nvidia)
- CPU: x86_64 / ARM64
Tested Configurations:
- GPU: AMD Ryzen 8000 Series iGPU (DirectML)
- CPU: AMD Ryzen CPU
Citation
@article{wang2023openchat,
title={OpenChat: Advancing Open-source Language Models with Mixed-Quality Data},
author={Wang, Guan and Cheng, Sijie and Zhan, Xianyuan and Li, Xiangang and Song, Sen and Liu, Yang},
journal={arXiv preprint arXiv:2309.11235},
year={2023}
}
Model info
Created: 2024-06-17
Updated: 2024-06-17
View on Hugging Face