cfahlgren1 HF Staff commited on
Commit
639eeb6
·
verified ·
1 Parent(s): 6f8d8d2

rename the app to offlinepage.app

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -72,18 +72,18 @@ model-index:
72
  <p align="center">
73
  <a href="https://huggingface.co/spaces/cfahlgren1/enron-autocomplete"><b>Try the demo&nbsp;→</b></a>
74
  &nbsp;&nbsp;·&nbsp;&nbsp;
75
- <a href="https://github.com/cfahlgren1/offline-page"><b>Write with it in offline.page&nbsp;→</b></a>
76
  </p>
77
 
78
  <br>
79
 
80
- tinynext is the autocomplete in [offline.page](https://github.com/cfahlgren1/offline-page). The app uses **v2**, in [`v2/`](https://huggingface.co/paperweight/tinynext/tree/main/v2). The files at the root are v1, the original character model, the same as [`cfahlgren1/enron-autocomplete`](https://huggingface.co/cfahlgren1/enron-autocomplete).
81
 
82
  ## v2: the next few words, with context
83
 
84
  <sub>In [`v2/`](https://huggingface.co/paperweight/tinynext/tree/main/v2). The files at the root of this repo are still v1.</sub>
85
 
86
- v1 guesses one letter at a time, so its suggestions are short word endings. v2 is a **12.5M-parameter transformer that predicts word pieces**, so one step can be a whole word, and it reads up to about 1,500 characters before the cursor (and, when there is any, text after it). It's the autocomplete in offline.page, running in a Web Worker.
87
 
88
  **How much typing it saves.** Every model is scored by [`v2/eval.py`](v2/eval.py) on the same held-out text: type it character by character, pause every 12 characters, and count a suggestion only if the text really continues that way. Same decoding rule and 50% cutoff as the app, suggestions of 4+ characters.
89
 
@@ -141,7 +141,7 @@ The browser computes in float32 on purpose: onnxruntime-web's int8 kernels were
141
 
142
  **Limits.**
143
 
144
- - offline.page only suggests at the end of a paragraph, so the text after the cursor is the next paragraph. Mid-line suggestions, where fill-in-the-middle should help most, aren't built yet.
145
  - It still leans toward office email, and it only sees keyboard characters.
146
  - It's English only.
147
 
@@ -202,10 +202,10 @@ The model knows how sure it is of each guess. You pick a cutoff, and it only sug
202
  |---|---|---|
203
  | 20% | 30% of the time | 48% |
204
  | 35% | 18% of the time | 66% |
205
- | **50%** *(offline.page)* | **11% of the time** | **80%** |
206
  | 70% | 7% of the time | 90% |
207
 
208
- The demo uses 40%, and offline.page uses 50%.
209
 
210
  These numbers come from 5,000 places in emails from people the model never saw in training. “Right” means the suggestion exactly matched what the person typed next.
211
 
@@ -277,5 +277,5 @@ hf jobs uv run --flavor a10g-large --secrets HF_TOKEN train.py --repo your-name/
277
  <br>
278
 
279
  <p align="center">
280
- <sub>tinynext 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/paperweight/tinyfix">tinyfix</a>, fixes typos from context.<br>Both are made by <a href="https://huggingface.co/paperweight">paperweight</a>, purpose-built small models.</sub>
281
  </p>
 
72
  <p align="center">
73
  <a href="https://huggingface.co/spaces/cfahlgren1/enron-autocomplete"><b>Try the demo&nbsp;→</b></a>
74
  &nbsp;&nbsp;·&nbsp;&nbsp;
75
+ <a href="https://offlinepage.app"><b>Write with it in offlinepage.app&nbsp;→</b></a>
76
  </p>
77
 
78
  <br>
79
 
80
+ tinynext is the autocomplete in [offlinepage.app](https://offlinepage.app). The app uses **v2**, in [`v2/`](https://huggingface.co/paperweight/tinynext/tree/main/v2). The files at the root are v1, the original character model, the same as [`cfahlgren1/enron-autocomplete`](https://huggingface.co/cfahlgren1/enron-autocomplete).
81
 
82
  ## v2: the next few words, with context
83
 
84
  <sub>In [`v2/`](https://huggingface.co/paperweight/tinynext/tree/main/v2). The files at the root of this repo are still v1.</sub>
85
 
86
+ v1 guesses one letter at a time, so its suggestions are short word endings. v2 is a **12.5M-parameter transformer that predicts word pieces**, so one step can be a whole word, and it reads up to about 1,500 characters before the cursor (and, when there is any, text after it). It's the autocomplete in offlinepage.app, running in a Web Worker.
87
 
88
  **How much typing it saves.** Every model is scored by [`v2/eval.py`](v2/eval.py) on the same held-out text: type it character by character, pause every 12 characters, and count a suggestion only if the text really continues that way. Same decoding rule and 50% cutoff as the app, suggestions of 4+ characters.
89
 
 
141
 
142
  **Limits.**
143
 
144
+ - offlinepage.app only suggests at the end of a paragraph, so the text after the cursor is the next paragraph. Mid-line suggestions, where fill-in-the-middle should help most, aren't built yet.
145
  - It still leans toward office email, and it only sees keyboard characters.
146
  - It's English only.
147
 
 
202
  |---|---|---|
203
  | 20% | 30% of the time | 48% |
204
  | 35% | 18% of the time | 66% |
205
+ | **50%** *(offlinepage.app)* | **11% of the time** | **80%** |
206
  | 70% | 7% of the time | 90% |
207
 
208
+ The demo uses 40%, and offlinepage.app uses 50%.
209
 
210
  These numbers come from 5,000 places in emails from people the model never saw in training. “Right” means the suggestion exactly matched what the person typed next.
211
 
 
277
  <br>
278
 
279
  <p align="center">
280
+ <sub>tinynext is one of two tiny models behind <a href="https://offlinepage.app">offlinepage.app</a>, a writing app that works in airplane mode.<br>Its partner, <a href="https://huggingface.co/paperweight/tinyfix">tinyfix</a>, fixes typos from context.<br>Both are made by <a href="https://huggingface.co/paperweight">paperweight</a>, purpose-built small models.</sub>
281
  </p>