Veyra3 5M Base ONNX INT8

Dynamic-sequence INT8 ONNX export for Veyra3 5M Base.

This ONNX model accepts dynamic sequence lengths, so generation loops may feed growing input_ids without hitting a fixed [1, 128] input-shape error.

Downloads last month
39
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including veyra-ai/veyra3-5m-base-onnx-int8