Tokenizer, model configuration, and generation configuration are included at the repository root. The redundant uncached decoder exports are intentionally omitted.

Usage with Transformers.js

import {
  AutoModelForSeq2SeqLM,
  AutoTokenizer,
} from "@huggingface/transformers";

const modelId = "imrahamed/coedit-large-webgpu-onnx";
const tokenizer = await AutoTokenizer.from_pretrained(modelId);
const model = await AutoModelForSeq2SeqLM.from_pretrained(modelId, {
  device: "webgpu",
  dtype: "fp32",
});

const input = await tokenizer(
  "Paraphrase the sentence: The application performs all inference locally.",
);
const output = await model.generate({
  inputs: input.input_ids,
  attention_mask: input.attention_mask,
  max_new_tokens: 64,
});
console.log(tokenizer.decode(output.tolist()[0], {
  skip_special_tokens: true,
}));

CoEdIT task prompts

Feature	Prompt
Grammar	`Fix grammatical errors in this sentence: {text}`
Formal	`Make the sentence formal: {text}`
Casual	`Change the style to casual: {text}`
Simplify	`Make the sentence simpler: {text}`
Rewrite	`Paraphrase the sentence: {text}`

Export details

Architecture: FLAN-T5 Large / CoEdIT
Format: ONNX, FP32
Opset: 18
Export task: text2text-generation-with-past
Optimization: Optimum ONNX Runtime O2
Intended execution provider: ONNX Runtime WebGPU
CPU/WASM fallback should be provided by the consuming application.

The export was validated against the source model. Small floating-point differences from ONNX graph optimization may occur.

License and attribution

Noncommercial use only. This derivative export follows the upstream Creative Commons Attribution-NonCommercial 4.0 license. See the source model card for training details, limitations, and attribution.