amd/Exaone-3.5-2.4B-instruct-onnx-ryzenai-hybrid
Introduction
This model was prepared using the AMD Quark Quantization tool, followed by necessary post-processing. Model generated using Ryzen AI 1.6.0. Compiled ops for 3K context length support located indd_plugins. Thedd_pluginsdirectory must be one level above the root model directory to be properly found.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for amd/Exaone-3.5-2.4B-Instruct-onnx-ryzenai-hybrid
Base model
deepseek-ai/DeepSeek-R1-Distill-Llama-8B