Static 8x256 WebGPU build of gradient-ai-text-detector

000aa19 verified about 1 month ago

1.6 kB

library_name: transformers.js
base_model: batmac/gradient-ai-text-detector-onnx
base_model_relation: quantized
pipeline_tag: text-classification
language:
  - en
license: mit
tags:
  - onnx
  - webgpu
  - ai-generated-text-detection
  - deberta-v2

Gradient AI-text detector, static 8x256 for WebGPU

A browser-oriented build of ShantanuT01/gradient-ai-text-detector (DeBERTa-v3-large, MIT), made from the 4-bit ONNX export batmac/gradient-ai-text-detector-onnx at revision 776d0164ba0de631036c70f6a146d68a7cd4ea4e.

The weights are unchanged. Two graph changes make it fast on onnxruntime-web's WebGPU provider:

Each relative-attention GatherElements(data, Expand(idx)) becomes an equivalent flat Gather with an [L, L] index, so no [batch*heads, L, L] int64 tensor is built each run.
The input shape is fixed at batch 8 x 256 tokens and all shape arithmetic is constant-folded, so nothing round-trips GPU -> CPU mid-run.

In Firefox this takes a full batch from ~5.3 s to ~3.5 s, about 0.44 s per passage.

Usage

Inputs must be exactly input_ids and attention_mask of shape [8, 256] (int64). Right-pad with token 0 and mask 0. Output logits is [8, 1]; apply a sigmoid yourself. The score is the raw classifier output, not a calibrated probability.

Built by scripts/build-model.sh in the Deckard (in-browser) Firefox extension. Not endorsed by the model authors or Microsoft. Do not use as the sole basis for high-stakes decisions.