kobkrit commited on
Commit
9322954
·
verified ·
1 Parent(s): 4f5f205

v1.3: live Windows 11 + macOS grounding, point_refine

Browse files
Files changed (3) hide show
  1. README.md +101 -66
  2. model.safetensors +1 -1
  3. types.py +3 -0
README.md CHANGED
@@ -6,13 +6,15 @@ tags: [system-one, decision-model, gui-grounding, computer-use, voice-control, t
6
  base_model: Qwen/Qwen3.5-0.8B-Base
7
  ---
8
 
9
- # OpenThai-SystemOne-Vision (v1.1)
10
 
11
  The vision variant of [OpenThai-SystemOne](https://huggingface.co/iapp/OpenThai-SystemOne): the same open Thai + English
12
  System One decision model, now with **images in the state** and a fourth question type, **`point`**, that returns where
13
  on a screenshot something is. Screenshot in, click out, in one forward pass, no text generation.
14
 
15
- **v1.1 (2026-09-24)** adds Thai **voice-command understanding** for hands-free computer control (a spoken Thai command +
 
 
16
  the app and window title in, the operation and its target out) and stronger desktop and Doom play. See [Versions](#versions).
17
 
18
  | | OpenThai-SystemOne (text) | OpenThai-SystemOne-Vision |
@@ -68,96 +70,122 @@ state = 'คำสั่งเสียงภาษาไทยจากผู
68
 
69
  ## Evaluation
70
 
71
- All numbers are for this checkpoint (v1.1) next to v1.0 and the text model v0.3, measured with the same scripts, single
72
- option order (no permutation averaging) unless noted. Accuracy in %.
 
 
73
 
74
- ### GUI grounding (`point`: predicted click inside the target box)
75
- | benchmark | v1.0 | **v1.1** | notes |
76
- |---|---|---|---|
77
- | ScreenSpot-v2, all (1,272) | 82.7 | **80.7** | reference: GUI-Actor-2B 88.6, Qwen3-VL-2B 86.7, UI-TARS-1.5-7B 89.0 (published) |
78
- | · desktop text / icon (194 / 140) | 90.2 / 71.4 | 89.7 / **74.3** | |
79
- | · mobile text / icon (290 / 211) | 95.9 / 71.1 | 94.5 / 70.6 | |
80
- | · web text / icon (234 / 203) | 87.6 / 70.9 | 85.0 / 62.1 | web icons: the main regression of v1.1 |
81
- | Desktop (OS-Atlas macOS / Windows / Linux, held-out, 1,028) | 39.2 | **50.6** | |
82
- | Desktop "not on screen" abstention (26) | 38.5 | **80.8** | small set |
83
- | Thai GUI held-out domains, `point` (1,611) | 80.1 | 78.0 | teacher-written Thai/English instructions on unseen Thai sites |
84
- | Thai GUI set-of-marks `choice` (476) | 92.9 | **93.5** | pick the element index from the element table |
85
- | Thai GUI `operation` choice (476) | 99.8 | 99.6 | CLICK / TYPE_TEXT / SELECT |
86
- | Thai screen QA `noul` / `choice` (623 / 341) | 94.9 / 85.0 | 93.9 / 84.8 | is a dialog open, which page type, is there a form… |
87
- | Thai GUI "not on screen" abstention (179) | 45.8 | 46.4 | known weak spot: check `abstain` before clicking |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
  ### Thai voice commands (operation + slots from one spoken sentence)
90
- | set | v1.0 | **v1.1** | notes |
91
- |---|---|---|---|
92
- | real commands spoken in use, operation (183) | 65.0 | **88.5** | hand-labelled from a live macOS voice-control session |
93
- | · slots (site / app / key / Nth) when the operation is right | 90.7 | **100.0** | |
94
- | · chit-chat between commands acted on (41) | 14.6 | **7.3** | lower is better |
95
- | real off-command conversation picked up by the microphone, acted on (227) | 3.5 | **2.6** | lower is better; before the controller's safety checks |
96
- | synthetic voice commands, held out (1,406 questions) | 61.2 | **90.5** | |
97
- | synthetic hard cases (fragments, site vs app, ordinals, 446 questions) | 55.0 | **90.8** | |
98
-
99
- ### Doom from pixels (`demo/doom_demo.py`, defend_the_center, skill 3, 20 episodes, seed 1234)
100
- | input | v1.0 kills / episode | **v1.1 kills / episode** | ms / decision (H100) |
101
  |---|---|---|---|
102
- | two 320×240 frames only | 5.5 | **11.9** (1–22) | 50 |
103
- | frames + symbolic state | 6.0 | 6.4 | 49 |
104
- | symbolic state only (text) | 7.3 | **8.7** | 40 |
105
- | the privileged scripted expert it imitates | 6.8 | 6.8 | – |
 
 
 
 
 
 
 
 
106
 
107
- Offline Doom decisions (600 frames): move 87.2, attack 96.8, in-danger 96.5, nearest-enemy point 52.9, enemy-absent 96.6.
108
 
109
  ### Text-only tasks
110
  Public 13-subset benchmark (the Bespoke / Jev public suite; `noul`/`choice` = accuracy, `score` = exact level):
111
 
112
- | subset | v0.3 | v1.0 | **v1.1** | Jev 1.13.0* | Nimble-9B* |
113
  |---|---|---|---|---|---|
114
- | aegis2 | 83.2 | 84.4 | 82.0 | 80.4 | 81.2 |
115
- | boolq | 79.7 | 80.0 | 79.7 | 89.7 | 86.0 |
116
- | civil_comments | 79.0 | 74.0 | **86.0** | 81.0 | 70.3 |
117
- | helpsteer2 (score) | 41.6 | 41.6 | 42.0 | 34.1 | 39.0 |
118
- | massive-de-DE | 88.3 | 89.4 | 89.4 | 86.9 | 83.4 |
119
- | massive-en-US | 88.3 | 88.9 | 89.4 | 87.4 | 86.9 |
120
- | multinli | 89.0 | 88.3 | 89.0 | 82.9 | 85.3 |
121
- | paws | 94.0 | 93.6 | 94.0 | 89.2 | 82.8 |
122
- | pubmedqa | 64.0 | 69.2 | 67.6 | 77.2 | 75.6 |
123
- | squad2 | 89.3 | 89.6 | 89.0 | 82.9 | 80.6 |
124
- | summeval-consistency (score) | 75.0 | 71.5 | 75.0 | 81.2 | 75.7 |
125
- | summeval-relevance (score) | 21.7 | 19.2 | 21.2 | 35.0 | 49.2 |
126
- | vitaminc-dev | 72.5 | 70.3 | 71.3 | 80.1 | 76.6 |
127
- | **macro, 13 subsets** | 74.3 | 73.8 | **75.0** | 76.0 | 74.8 |
128
- | macro, 10 accuracy subsets | 82.7 | 82.8 | **83.7** | 83.8 | 80.9 |
129
 
130
  \* published by Bespoke Labs for their own harness on the same subsets (Jev via the TypeSafe API).
131
- With 8 option orders averaged: v1.1 macro 75.2 (10 accuracy subsets 84.0).
132
 
133
  Thai held-out and eval-split sets (`th` unless noted; banking77 and xLAM are English):
134
 
135
- | set | v0.3 | v1.0 | **v1.1** | v1.1, 8 orders |
136
  |---|---|---|---|---|
137
- | banking77 (77-way, whole dataset held out) | 45.4 | 57.5 | **62.0** | 64.6 |
138
- | contrastive pairs, one-fact flips | 80.7 | 81.4 | **82.1** | 81.1 |
139
- | MASSIVE-th intent | 90.0 | 90.8 | **91.1** | 92.0 |
140
- | Prachathai topics | 98.1 | 98.7 | 98.7 | 98.7 |
141
- | SIB-200 Thai topic (whole dataset held out) | 77.9 | 76.5 | 75.5 | 76.5 |
142
- | Wisesight sentiment (whole dataset held out) | 51.6 | 52.6 | 52.8 | 52.0 |
143
- | Wongnai stars (score, exact) | 63.5 | 63.1 | 63.1 | 63.1 |
144
- | xLAM tool selection | 99.4 | 99.4 | 99.3 | 99.4 |
145
- | XNLI-th | 77.1 | 76.3 | 75.6 | 75.8 |
146
- | **macro, 8 accuracy sets** | 77.5 | 79.1 | **79.6** | 80.0 |
147
 
148
  ### Latency (batch 1, H100, end-to-end `SystemOneClient`)
149
  | request | tokens | ms |
150
  |---|---|---|
151
  | two 320×240 game frames + short state, 2 questions | 298 (160 visual) | 50 |
152
  | 1280×800 screenshot + goal, `point` + `choice` | 1,062 (1,000 visual) | 52 |
 
153
  | text only (3-question Thai ticket) | 166 | ~40 |
154
- | voice command intent (6 questions, up to 250 app names) | ~2,000 | 100–250 round trip from a Mac to a remote GPU, incl. HTTP |
155
 
156
  ## Versions
157
 
158
  | version | date | change |
159
  |---|---|---|
160
- | **v1.1** | 2026-09-24 | + Thai voice-command intents (28k synthetic training records from 21k distinct commands + 8.9k hard-case records: fragments / chit-chat = NONE, site vs app, ordinal + topic, ASR spelling variants), desktop grounding round (OS-Atlas macOS / Windows / Linux), text-anchor round (civil_comments, VitaminC); temperatures recalibrated. Voice 65 → 88.5, desktop 39 → 51, Doom pixels 5.5 → 11.9 kills, ScreenSpot-v2 82.7 → 80.7. |
 
161
  | v1.0 | 2026-09-23 | first vision release (Thai GUI crawl, public grounding, Doom rollouts, screen QA on the v0.3 text tower) |
162
 
163
  ## How it was built
@@ -172,9 +200,16 @@ Thai held-out and eval-split sets (`th` unless noted; banking77 and xLAM are Eng
172
  4. v1.1: a text-anchor round and a desktop round averaged into one checkpoint, then a voice-command round
173
  (label-conditioned generation by a teacher LLM, every sentence blind re-labelled and kept only on agreement) and a
174
  hard-case round aimed at the mistakes seen in real use; the rest of the mix is rehearsed at the same time.
175
- 5. Calibration of the per-type temperatures.
 
 
 
 
 
 
176
 
177
  ## License & credits
178
 
179
  Apache-2.0. Built by iApp Technology / OpenThaiGPT on Qwen3.5-0.8B-Base. GUI grounding recipe after GUI-Actor; System One
180
- contract after TypeSafe AI's Jev.
 
 
6
  base_model: Qwen/Qwen3.5-0.8B-Base
7
  ---
8
 
9
+ # OpenThai-SystemOne-Vision (v1.3)
10
 
11
  The vision variant of [OpenThai-SystemOne](https://huggingface.co/iapp/OpenThai-SystemOne): the same open Thai + English
12
  System One decision model, now with **images in the state** and a fourth question type, **`point`**, that returns where
13
  on a screenshot something is. Screenshot in, click out, in one forward pass, no text generation.
14
 
15
+ **v1.3 (2026-09-26)** clicks better on real Windows and Mac apps (trained on live Windows 11 and macOS screens) and on
16
+ large screens, and adds `point_refine`;
17
+ **v1.1 (2026-09-24)** added Thai **voice-command understanding** for hands-free computer control (a spoken Thai command +
18
  the app and window title in, the operation and its target out) and stronger desktop and Doom play. See [Versions](#versions).
19
 
20
  | | OpenThai-SystemOne (text) | OpenThai-SystemOne-Vision |
 
70
 
71
  ## Evaluation
72
 
73
+ v1.3 next to v1.1 (the previous published version), same scripts; single option order unless noted; accuracy in %.
74
+ "default" = the plain API call (screenshot at ≤ 1280×800); "+ refine" = screenshot at 2 MP (`"detail": "high"`) with
75
+ `point_refine` over the top-3 first-pass candidates, landscape screens only: zoom 50 % on ScreenSpot-v2 / Thai GUI / OS-Atlas,
76
+ 35 % on Windows / Mac live and ScreenSpot-Pro. On desktops and large screens, send `"detail": "high"` and `point_refine`.
77
 
78
+ ### Live desktops (new): real apps, click targets from the accessibility tree
79
+ | benchmark | v1.1 default | **v1.3 default** | **v1.3 + refine** | Qwen3-VL-2B | Qwen3-VL-4B |
80
+ |---|---|---|---|---|---|
81
+ | **Windows live** (319 targets, 28 screens of Windows 11: Settings, File Explorer, Control Panel, Notepad, Paint, Calculator, Store, Edge, …) | 63.3 | **68.3** | **69.3** | 67.1 | 73.0 |
82
+ | · Windows Settings pages (114) | 64.9 | 69.3 | – | 66.7 | 68.4 |
83
+ | **Mac live** (358 targets, 29 screens: System Settings, Finder, Safari, Office, iWork, …) | 65.4 | 63.7 | 67.6 | 67.0 | 67.9 |
84
+ | · label-checked (340: 18 targets found unanswerable removed) | 68.5 | 66.8 | **71.2** | 70.6 | 71.5 |
85
+ | latency per click (H100, eval harness) | ~70 ms | ~70 ms | 0.1–0.25 s | ~0.9 s | ~0.75 s |
86
+
87
+ The Windows and Mac live screens are never trained on. v1.3's training data does include *other* screens of the same apps
88
+ (for example other Settings pages), captured the same way. Weak spots: Windows Calculator (60; its buttons are named with
89
+ words such as "Two" and "Multiply by", Qwen3-VL-4B 95), icon-only tiles, and small text links.
90
+
91
+ ### GUI grounding benchmarks (`point`: predicted click inside the target box)
92
+ | benchmark | v1.1 default | **v1.3 default** | **v1.3 + refine** | Qwen3-VL-2B | Qwen3-VL-4B |
93
+ |---|---|---|---|---|---|
94
+ | ScreenSpot-v2, all (1,272) | 80.7 | **82.2** | **85.2** | 85.8 | 90.4 |
95
+ | · desktop text / icon | 89.7 / 74.3 | 90.2 / 75.7 | 91.8 / 83.6 | 93.8 / 82.9 | 96.9 / 85.7 |
96
+ | · mobile text / icon | 94.5 / 70.6 | 94.5 / 71.6 | 93.8 / 74.9 | 94.1 / 82.0 | 96.9 / 83.4 |
97
+ | · web text / icon | 85.0 / 62.1 | 84.2 / 70.0 | 88.5 / 74.9 | 85.9 / 72.4 | 91.9 / 83.7 |
98
+ | ScreenSpot-Pro (1,581, 26 pro apps at up to 4K: Windows / macOS / Linux) | 9.8* | 9.0 | **32.9** (29.3 / 38.7 / 28.0) | 43.4* | 54.8* |
99
+ | Desktop (OS-Atlas macOS / Windows / Linux, held-out) | 50.6 | **53.7** | 59.8 (600) | 63.8 | 65.6 |
100
+ | Desktop "not on screen" abstention (26) | 80.8 | **92.3** | – | – | – |
101
+ | Thai GUI held-out domains, `point` | 78.0 | 77.8 | 76.7 (600) | 72.4 | 80.4 |
102
+ | Thai GUI set-of-marks `choice` / `operation` | 93.5 / 99.6 | 93.1 / 99.6 | – | – | – |
103
+ | Thai screen QA `noul` / `choice` | 93.9 / 84.8 | 93.1 / 85.9 | – | – | – |
104
+ | Thai GUI "not on screen" abstention | 46.4 | 48.0 | – | – | – |
105
+
106
+ Qwen3-VL numbers: our runs with the same harness (screenshot + instruction, click inside the box); * every 2nd ScreenSpot-Pro
107
+ item (790).
108
+
109
+ ### Better clicks on large screens: `point_refine`
110
+ ```python
111
+ r = c.system_one("goal: …", {"where": {"type": "point", "instructions": "ปุ่มบันทึก", "image": "s"}},
112
+ images=[{"id": "s", "path": "screen.png", "role": "screenshot", "detail": "high"}],
113
+ point_refine={"zoom": 0.35, "cands": 3}) # HTTP API: "point_refine": {...} or true
114
+ ```
115
+ The first pass points on the whole screen; the client then re-points on a crop around each of the top candidates at native
116
+ detail and keeps the most confident. It only zooms landscape screens larger than the pixel budget (zooming phone screenshots
117
+ hurts). ScreenSpot-Pro 9.0 → 32.9, ScreenSpot-v2 82.2 → 85.2, Mac live 66.8 → 71.2 (checked). Cost: 1 + `cands` forward passes.
118
 
119
  ### Thai voice commands (operation + slots from one spoken sentence)
120
+ | set | v1.0 | v1.1 | **v1.3** |
 
 
 
 
 
 
 
 
 
 
121
  |---|---|---|---|
122
+ | real commands spoken in use, operation (183) | 65.0 | 88.5 | **89.6** |
123
+ | · slots (site / app / key / Nth) when the operation is right | 90.7 | 100.0 | **100.0** |
124
+ | · chit-chat between commands acted on (41), lower is better | 14.6 | 7.3 | 7.3 |
125
+ | real off-command conversation picked up by the microphone, acted on (227), lower is better | 3.5 | 2.6 | 4.4 |
126
+ | synthetic voice commands, held out (1,406 questions) | 61.2 | 90.5 | **92.0** |
127
+ | synthetic hard cases (fragments, site vs app, ordinals, 446 questions) | 55.0 | 90.8 | **93.3** |
128
+
129
+ ### Doom from pixels (`demo/doom_demo.py`, defend_the_center, skill 3, 40 episodes, seed 999)
130
+ | input | v1.0 | v1.1 | **v1.3** | ms / decision |
131
+ |---|---|---|---|---|
132
+ | two 320×240 frames only | 5.5 (20 eps) | 11.8 | **13.0** (1–23) | 49 |
133
+ | the privileged scripted expert it imitates | 6.8 | 6.8 | 6.8 | – |
134
 
135
+ Offline Doom decisions (600 frames): move 88.2, attack 97.0, in-danger 96.3, nearest-enemy point 51.1, enemy-absent 96.6.
136
 
137
  ### Text-only tasks
138
  Public 13-subset benchmark (the Bespoke / Jev public suite; `noul`/`choice` = accuracy, `score` = exact level):
139
 
140
+ | subset | v0.3 | v1.1 | **v1.3** | Jev 1.13.0* | Nimble-9B* |
141
  |---|---|---|---|---|---|
142
+ | aegis2 | 83.2 | 82.0 | 82.0 | 80.4 | 81.2 |
143
+ | boolq | 79.7 | 79.7 | 79.7 | 89.7 | 86.0 |
144
+ | civil_comments | 79.0 | 86.0 | **86.3** | 81.0 | 70.3 |
145
+ | helpsteer2 (score) | 41.6 | 42.0 | 40.4 | 34.1 | 39.0 |
146
+ | massive-de-DE | 88.3 | 89.4 | 89.7 | 86.9 | 83.4 |
147
+ | massive-en-US | 88.3 | 89.4 | **90.3** | 87.4 | 86.9 |
148
+ | multinli | 89.0 | 89.0 | 88.3 | 82.9 | 85.3 |
149
+ | paws | 94.0 | 94.0 | 94.0 | 89.2 | 82.8 |
150
+ | pubmedqa | 64.0 | 67.6 | 67.2 | 77.2 | 75.6 |
151
+ | squad2 | 89.3 | 89.0 | 88.6 | 82.9 | 80.6 |
152
+ | summeval-consistency (score) | 75.0 | 75.0 | 75.0 | 81.2 | 75.7 |
153
+ | summeval-relevance (score) | 21.7 | 21.2 | 20.4 | 35.0 | 49.2 |
154
+ | vitaminc-dev | 72.5 | 71.3 | 71.0 | 80.1 | 76.6 |
155
+ | **macro, 13 subsets** | 74.3 | 75.0 | 74.8 | 76.0 | 74.8 |
156
+ | macro, 10 accuracy subsets | 82.7 | 83.7 | 83.7 | 83.8 | 80.9 |
157
 
158
  \* published by Bespoke Labs for their own harness on the same subsets (Jev via the TypeSafe API).
 
159
 
160
  Thai held-out and eval-split sets (`th` unless noted; banking77 and xLAM are English):
161
 
162
+ | set | v0.3 | v1.1 | **v1.3** | v1.3, 8 orders |
163
  |---|---|---|---|---|
164
+ | banking77 (77-way, whole dataset held out) | 45.4 | 62.0 | 62.0 | 64.6 |
165
+ | contrastive pairs, one-fact flips | 80.7 | 82.1 | 82.1 | 80.4 |
166
+ | MASSIVE-th intent | 90.0 | 91.1 | 91.1 | 91.9 |
167
+ | Prachathai topics | 98.1 | 98.7 | 98.6 | 98.7 |
168
+ | SIB-200 Thai topic (whole dataset held out) | 77.9 | 75.5 | 75.5 | 77.0 |
169
+ | Wisesight sentiment (whole dataset held out) | 51.6 | 52.8 | 52.5 | 51.9 |
170
+ | Wongnai stars (score, exact) | 63.5 | 63.1 | 63.3 | 63.3 |
171
+ | xLAM tool selection | 99.4 | 99.3 | 99.4 | 99.3 |
172
+ | XNLI-th | 77.1 | 75.6 | 75.5 | 75.6 |
173
+ | **macro, 8 accuracy sets** | 77.5 | 79.6 | 79.6 | 79.9 |
174
 
175
  ### Latency (batch 1, H100, end-to-end `SystemOneClient`)
176
  | request | tokens | ms |
177
  |---|---|---|
178
  | two 320×240 game frames + short state, 2 questions | 298 (160 visual) | 50 |
179
  | 1280×800 screenshot + goal, `point` + `choice` | 1,062 (1,000 visual) | 52 |
180
+ | large screenshot at `"detail": "high"` + `point_refine` (3 candidates), eval harness | ~2,000 visual per pass | ~135 (FHD) – 245 (4K) |
181
  | text only (3-question Thai ticket) | 166 | ~40 |
 
182
 
183
  ## Versions
184
 
185
  | version | date | change |
186
  |---|---|---|
187
+ | **v1.3** | 2026-09-26 | + live desktop grounding: 665 records from 319 live Windows 11 screens (UI Automation targets; Settings, Control Panel, dialogs, shell folders, Calculator modes, Store, Edge) and 386 records from 116 live macOS screens (accessibility targets; System Settings, Finder, utilities, Safari, Word / Excel / PowerPoint / Pages ribbons), with account names blacked out; on top of an internal v1.2 round (ShowUI desktop + web, 40k zoomed crops, 75k xlangai/Jedi records, 2 MP training, averaged with v1.1). Client / API `point_refine`. Windows live 63.3 → 68.3, ScreenSpot-v2 80.7 → 82.2 (85.2 with refine), ScreenSpot-Pro ~10 → 32.9 with refine, OS-Atlas desktop 50.6 → 53.7, Doom 11.8 → 13.0, text and Thai unchanged. |
188
+ | v1.1 | 2026-09-24 | + Thai voice-command intents (28k synthetic training records from 21k distinct commands + 8.9k hard-case records: fragments / chit-chat = NONE, site vs app, ordinal + topic, ASR spelling variants), desktop grounding round (OS-Atlas macOS / Windows / Linux), text-anchor round (civil_comments, VitaminC); temperatures recalibrated. Voice 65 → 88.5, desktop 39 → 51, Doom pixels 5.5 → 11.9 kills, ScreenSpot-v2 82.7 → 80.7. |
189
  | v1.0 | 2026-09-23 | first vision release (Thai GUI crawl, public grounding, Doom rollouts, screen QA on the v0.3 text tower) |
190
 
191
  ## How it was built
 
200
  4. v1.1: a text-anchor round and a desktop round averaged into one checkpoint, then a voice-command round
201
  (label-conditioned generation by a teacher LLM, every sentence blind re-labelled and kept only on agreement) and a
202
  hard-case round aimed at the mistakes seen in real use; the rest of the mix is rehearsed at the same time.
203
+ 5. v1.2 (internal): three grounding rounds from v1.1 (ShowUI desktop + web and 2 MP screenshots; 40k zoomed crops at native detail
204
+ that teach the `point_refine` second pass; 75k xlangai/Jedi records), with voice, text and Doom rehearsed; the release is
205
+ the equal-weight average of v1.1 and the last round, which kept v1.1's Thai GUI and Doom skills and the new desktop gains.
206
+ 6. v1.3: one round from v1.2 with live Windows 11 and macOS screens captured through the accessibility APIs (a small
207
+ agent inside a Windows VM; the macOS accessibility tree), other apps / pages than the live eval screens, personal names
208
+ blacked out, rest of the mix rehearsed.
209
+ 7. Calibration of the per-type temperatures.
210
 
211
  ## License & credits
212
 
213
  Apache-2.0. Built by iApp Technology / OpenThaiGPT on Qwen3.5-0.8B-Base. GUI grounding recipe after GUI-Actor; System One
214
+ contract after TypeSafe AI's Jev. Grounding data from OS-Atlas, ShowUI, Wave-UI, GroundUI and Jedi (OSWorld-G);
215
+ benchmarks ScreenSpot-v2 and ScreenSpot-Pro.
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2b257815523a460751cf0fded102ac103ea9c46df8de645eda9bef0bd429bc4
3
  size 1724708176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c302e4660e4a6af3135309740a59ad1819b9483b1a436487e4bd8fdafe6a5217
3
  size 1724708176
types.py CHANGED
@@ -160,6 +160,9 @@ class SystemOneRequest(BaseModel):
160
  permutations: Optional[int] = Field(default=None, ge=1, le=32)
161
  # vision variant: up to 4 images; text-only models reject requests that carry images or point questions.
162
  images: Optional[List[ImageInput]] = None
 
 
 
163
 
164
  @model_validator(mode="after")
165
  def _non_empty(self):
 
160
  permutations: Optional[int] = Field(default=None, ge=1, le=32)
161
  # vision variant: up to 4 images; text-only models reject requests that carry images or point questions.
162
  images: Optional[List[ImageInput]] = None
163
+ # vision variant: re-point `point` answers on zoomed crops (True = {"steps": 1, "zoom": 0.5, "adaptive": true}); helps small
164
+ # targets on large desktop screens, ~1 extra forward pass per step and point question.
165
+ point_refine: Optional[Union[bool, Dict[str, Any]]] = None
166
 
167
  @model_validator(mode="after")
168
  def _non_empty(self):