Configuration Parsing Warning:In config.json: "quantization_config.modules_to_not_convert" must be an array

IOL-AI 2026 Submission Model

This repository contains the AWQ-quantized weights for Microsoft's Phi-4, optimized for the IOL-AI 2026 challenge.

Hermes Invocation

"The hearer must be of one mind with the speaker, my son, and of one spirit as well; he must have hearing quicker than the speech of the speaker."

Downloads last month
61
Safetensors
Model size
15B params
Tensor type
I32
·
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support