new card with the tinyfix banner

README.md

@@ -6,52 +6,73 @@ tags:
   - spelling-correction
   - browser
   - onnx
+  - offline-page
 datasets:
   - HuggingFaceFW/fineweb-edu
   - HuggingFaceTB/smoltalk
   - OpenAssistant/oasst1
 ---
 
-# tinyfix
+<p align="center">
+  <img src="banner.png" alt="tinyfix: autocorrect that reads both sides of a word" width="880">
+</p>
 
-**Spell check can't tell that "form" was meant to be "from", since both are real words. This 2.1 MB model can.**
+<p align="center">
+  <img alt="params: 1.9M" src="https://img.shields.io/badge/params-1.9M-7b1fe0?style=flat-square&labelColor=1d1d1f">
+  <img alt="size: 2.1 MB" src="https://img.shields.io/badge/size-2.1%20MB-7b1fe0?style=flat-square&labelColor=1d1d1f">
+  <img alt="speed: ~3 ms / check" src="https://img.shields.io/badge/speed-~3%20ms%20%2F%20check-7b1fe0?style=flat-square&labelColor=1d1d1f">
+  <img alt="runs: in your browser" src="https://img.shields.io/badge/runs-in%20your%20browser-7b1fe0?style=flat-square&labelColor=1d1d1f">
+  <img alt="data sent: none" src="https://img.shields.io/badge/data%20sent-none-7b1fe0?style=flat-square&labelColor=1d1d1f">
+</p>
 
-![The tinyfix demo correcting "I recieve the report tomorow and we saw there new house." as it is typed](tinyfix.png)
+<h3 align="center">Spell check can't tell that “form” was meant to be “from”,<br>since both are real words. This 2.1 MB model can.</h3>
 
-**[Try it in your browser](https://huggingface.co/spaces/cfahlgren1/tinyfix)**
+<p align="center">
+  <a href="https://huggingface.co/spaces/cfahlgren1/tinyfix"><b>Try the demo&nbsp;→</b></a>
+  &nbsp;&nbsp;·&nbsp;&nbsp;
+  <a href="https://github.com/cfahlgren1/offline-page"><b>Write with it in offline.page&nbsp;→</b></a>
+</p>
 
-It reads the words on both sides of a correctly spelled word and picks the best fit from nearby real words. It runs on the page with [ONNX Runtime Web](https://onnxruntime.ai/docs/tutorials/web/), so nothing you type is sent anywhere.
+<br>
 
-| Parameters | Model size | Gzipped | Time per check |
-|---|---|---|---|
-| **1.9M** | **2.1 MB** | **1.6 MB** | **About 3 ms** in Chrome |
+tinyfix reads the words on both sides of a correctly spelled word and picks the best fit from nearby real words. It runs on the page with [ONNX Runtime Web](https://onnxruntime.ai/docs/tutorials/web/), so nothing you type is sent anywhere.
 
 ## What it does
 
+<p align="center">
+  <img src="tinyfix.png" alt="The tinyfix demo correcting “I recieve the report tomorow and we saw there new house.” as it is typed" width="760">
+</p>
+
 | You type | It becomes |
 |---|---|
-| I will send it **form** home tomorrow. | I will send it **from** home tomorrow. |
-| Let me **now** if that works. | Let me **know** if that works. |
-| We saw **there** new house. | We saw **their** new house. |
-| Please fill out the **form** and return it. | No change |
+| I will send it <del>form</del> home tomorrow. | I will send it **from** home tomorrow. |
+| Let me <del>now</del> if that works. | Let me **know** if that works. |
+| We saw <del>there</del> new house. | We saw **their** new house. |
+| Please fill out the **form** and return it. | *No change. “form” is right here.* |
 
 ## How well it works
 
+<table>
+  <tr>
+    <td align="center" width="33%"><h2>94%</h2>of its fixes are right</td>
+    <td align="center" width="33%"><h2>31%</h2>of real-word typos fixed<br><sub>in Eager mode</sub></td>
+    <td align="center" width="33%"><h2>~3 ms</h2>per check in Chrome</td>
+  </tr>
+</table>
+
 Measured on 2,460 real-word typos from GitHub commits and 45,000 correct words of email and documentation that it never trained on.
 
 | Setting | Real-word typos fixed | Fixes that were right | Correct email words changed | Correct GitHub words changed |
 |---|---|---|---|---|
-| Careful | **19%** | **94%** | About 1 in 2,500 | About 1 in 1,700 |
-| Eager | **31%** | **94%** | About 1 in 910 | About 1 in 430 |
-
-Careful is the default. The demo runs Eager, so you see more fixes.
+| Careful *(default)* | **19%** | **94%** | about 1 in 2,500 | about 1 in 1,700 |
+| Eager *(demo and offline.page)* | **31%** | **94%** | about 1 in 910 | about 1 in 430 |
 
 It also helps choose the right fix for misspelled words, raising that fix rate from 56% to 61.5% while 96.6% of fixes stay right.
 
 ### What it misses
 
-- It misses more real-word typos than it catches, including "don" typed for "do".
-- It can only judge the 20,000 words it knows, so a rarer word like "ware" typed for "were" is left alone.
+- It misses more real-word typos than it catches, including “don” typed for “do”.
+- It can only judge the 20,000 words it knows, so a rarer word like “ware” typed for “were” is left alone.
 - It needs the words that come after, so these fixes land a couple of words later.
 - English only.
 
@@ -59,6 +80,9 @@ It also helps choose the right fix for misspelled words, raising that fix rate f
 
 The model scores candidate words for one position in a sentence. Higher scores fit better, and comparing each candidate to the typed word tells you whether a swap is worth making.
 
+<details>
+<summary><b>Inputs and outputs</b></summary>
+
 | Name | Shape | What it holds |
 |---|---|---|
 | `left` (input) | `[batch, 16]` int64 | The words before, left-padded with 0, starting with `<s>` when there are fewer than 16 |
@@ -68,15 +92,26 @@ The model scores candidate words for one position in a sentence. Higher scores f
 
 IDs are line numbers in `wrong-word-vocab.txt`, starting from 0. Words are lowercased, and capitalized words in the middle of a sentence become `<name>`.
 
-## Files
+</details>
+
+<details>
+<summary><b>Files</b></summary>
 
 | File | What it is |
 |---|---|
 | `wrong-word.onnx` | The quantized model |
 | `wrong-word-vocab.txt` | The 20,000 words it knows, one per line |
-| `wrong-word-confusions.txt` | Mix-ups like "their" and "there" that are far apart on the keyboard |
+| `wrong-word-confusions.txt` | Mix-ups like “their” and “there” that are far apart on the keyboard |
 | `train_realword.py` | The training script |
 
+</details>
+
 ## Training
 
 A word-level GRU that reads 16 words before and up to 4 words after, trained for 25 minutes on an A10G. It learned from 118M tokens of [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu), [SmolTalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) and [OpenAssistant](https://huggingface.co/datasets/OpenAssistant/oasst1), by swapping real words for nearby real words and learning to swap them back.
+
+<br>
+
+<p align="center">
+  <sub>tinyfix is one of two tiny models behind <a href="https://github.com/cfahlgren1/offline-page">offline.page</a>, a writing app that works in airplane mode.<br>Its partner, <a href="https://huggingface.co/cfahlgren1/tinynext">tinynext</a>, suggests the next few words.</sub>
+</p>