README.md

---
license: apache-2.0
library_name: transformers.js
pipeline_tag: text-generation
tags:
  - coedit
  - flan-t5
  - text2text-generation
  - grammar
  - writing-assistant
  - onnx
  - webgpu
  - transformers.js
datasets:
  - grammarly/coedit
---

# Flint CoEdIT Base for WebGPU (ONNX)

Browser-ready ONNX export of the 250M-parameter CoEdIT Base checkpoint,
packaged for local sequence-to-sequence generation with Transformers.js and
ONNX Runtime WebGPU.

## Correct model lineage

This repository is an inference-format conversion, not a newly trained model
and not an export of `grammarly/coedit-large`.

| Role | Model or dataset |
| --- | --- |
| Foundation architecture | [`google/flan-t5-base`](https://huggingface.co/google/flan-t5-base) |
| Fine-tuned checkpoint converted here | [`jbochi/coedit-base`](https://huggingface.co/jbochi/coedit-base) |
| Fine-tuning dataset | [`grammarly/coedit`](https://huggingface.co/datasets/grammarly/coedit) |
| This ONNX export | [`imrahamed/coedit-base-webgpu-onnx`](https://huggingface.co/imrahamed/coedit-base-webgpu-onnx) |

Grammarly publishes the CoEdIT dataset and the official Large, XL, and XXL
checkpoints. It does not publish an official `grammarly/coedit-base`
checkpoint. The Base checkpoint converted here is the FLAN-T5 Base fine-tune
published by `jbochi`.

This repository contains only the two graphs required for cached browser generation:

- `onnx/encoder_model.onnx`
- `onnx/decoder_model_merged.onnx`

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

## Usage with Transformers.js

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

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

const input = await tokenizer(
  "Fix grammatical errors in this sentence: This are a test.",
);
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,
  }),
);
```

Expected output: `This is a test.`

## 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

- Foundation architecture: FLAN-T5 Base
- Converted checkpoint: `jbochi/coedit-base`
- Fine-tuning dataset: `grammarly/coedit`
- Parameters: approximately 250M
- 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

This derivative export follows the converted checkpoint's Apache 2.0 license.
See the [`jbochi/coedit-base` model
card](https://huggingface.co/jbochi/coedit-base) for its reported training
details and metrics. CoEdIT paper and dataset attribution remains applicable.