sk1729271/revision-assistant-rewrite-ai

Revision Assistant — Rewrite (AI)

Quantized ONNX + tokenizer for browser / Transformers.js inference in Revision Assistant.

Files

• onnx/model_quantized.onnx — int8 quantized weights (preferred for browser)
• tokenizer + config.json / ort_config.json / inference_config.json

Metrics / inference config

{
  "task": "ai",
  "prefix": "humanize AI scientific writing: ",
  "base": "google/flan-t5-small"
}

Full model.safetensors Flan-T5 checkpoint (~294MB). Not for browser; use for offline/server rewrite experiments.