Image-Text-to-Text
Transformers
Safetensors
inkling2_loop
weight-edit
browser-automation
conversational
8-bit precision
modelopt
Instructions to use husky8/Inkling-2-Mini-Fast-Browser-Use with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use husky8/Inkling-2-Mini-Fast-Browser-Use with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="husky8/Inkling-2-Mini-Fast-Browser-Use") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("husky8/Inkling-2-Mini-Fast-Browser-Use") model = AutoModelForMultimodalLM.from_pretrained("husky8/Inkling-2-Mini-Fast-Browser-Use", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use husky8/Inkling-2-Mini-Fast-Browser-Use with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "husky8/Inkling-2-Mini-Fast-Browser-Use" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "husky8/Inkling-2-Mini-Fast-Browser-Use", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/husky8/Inkling-2-Mini-Fast-Browser-Use
- SGLang
How to use husky8/Inkling-2-Mini-Fast-Browser-Use with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "husky8/Inkling-2-Mini-Fast-Browser-Use" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "husky8/Inkling-2-Mini-Fast-Browser-Use", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "husky8/Inkling-2-Mini-Fast-Browser-Use" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "husky8/Inkling-2-Mini-Fast-Browser-Use", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use husky8/Inkling-2-Mini-Fast-Browser-Use with Docker Model Runner:
docker model run hf.co/husky8/Inkling-2-Mini-Fast-Browser-Use
Show the edited model full width at its recorded speed
Browse files
benchmark/browser-speedups.mp4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4918da3d8e665b12719749670f14ed21511ca1511fea261070292e6937f9c800
|
| 3 |
+
size 3365575
|
benchmark/speedups-chapters.json
CHANGED
|
@@ -1,19 +1,19 @@
|
|
| 1 |
{
|
| 2 |
-
"sha256": "
|
| 3 |
"fps": 25,
|
| 4 |
"resolution": [
|
| 5 |
1200,
|
| 6 |
868
|
| 7 |
],
|
| 8 |
-
"duration_s":
|
| 9 |
-
"task_count":
|
| 10 |
-
"closing_start_s":
|
| 11 |
"playback_rate": 1,
|
| 12 |
"display_labels": [
|
| 13 |
"Original weights",
|
| 14 |
"Edited weights"
|
| 15 |
],
|
| 16 |
-
"selection": "One uninterrupted edited run per task at capture speed, followed by a labeled result still. Timings use the paired passing runs. The completed-order lookup uses the previously featured fastest take and appears once.",
|
| 17 |
"chapters": [
|
| 18 |
{
|
| 19 |
"number": 1,
|
|
@@ -300,54 +300,6 @@
|
|
| 300 |
{
|
| 301 |
"number": 7,
|
| 302 |
"start_s": 37.68,
|
| 303 |
-
"duration_s": 34.52,
|
| 304 |
-
"environment": "WebArena",
|
| 305 |
-
"task": "189",
|
| 306 |
-
"title": "Find the total of the latest pending order",
|
| 307 |
-
"arms": [
|
| 308 |
-
{
|
| 309 |
-
"arm": "Stock Inkling 2 Mini",
|
| 310 |
-
"elapsed_s": 33.850683916010894,
|
| 311 |
-
"passed": true,
|
| 312 |
-
"device": "M5 Max MacBook Pro",
|
| 313 |
-
"receipt_sha256": "9dd3fed47db798b1f67d44f794379eda89f3c949e8a10c0a65ced54dc05f5512",
|
| 314 |
-
"receipt": "189-original.json",
|
| 315 |
-
"recording": {
|
| 316 |
-
"kind": "native browser recording",
|
| 317 |
-
"source_sha256": "9d35421225e57628bada9376e92528ac7a677e5629efde93d4c44aa7661dd037",
|
| 318 |
-
"start_s": 0,
|
| 319 |
-
"source_duration_s": 33.85
|
| 320 |
-
},
|
| 321 |
-
"grader_status": "success"
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"arm": "Published stop-row weights",
|
| 325 |
-
"elapsed_s": 33.2397506670095,
|
| 326 |
-
"passed": true,
|
| 327 |
-
"device": "M5 Max MacBook Pro",
|
| 328 |
-
"receipt_sha256": "e26130900a6a30683ec77ad0f32b975f5f6f4be9b25df86c9e5caf1c800f16c1",
|
| 329 |
-
"receipt": "189-edited.json",
|
| 330 |
-
"recording": {
|
| 331 |
-
"kind": "native browser recording",
|
| 332 |
-
"source_sha256": "4b91334778448d041a1b3f59fa2188cd2cc44dbb0c14d5f8dfce324e6a9c8072",
|
| 333 |
-
"start_s": 0,
|
| 334 |
-
"source_duration_s": 33.45
|
| 335 |
-
},
|
| 336 |
-
"grader_status": "success"
|
| 337 |
-
}
|
| 338 |
-
],
|
| 339 |
-
"display_title": "Find the latest pending order total",
|
| 340 |
-
"playback_rate": 1.0,
|
| 341 |
-
"shown_arm": "edited",
|
| 342 |
-
"task_start_s": 0,
|
| 343 |
-
"task_end_s": 33.2397506670095,
|
| 344 |
-
"result_still_start_s": 70.92,
|
| 345 |
-
"result_still_duration_s": 1.28,
|
| 346 |
-
"frame_clock": "capture timestamps"
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"number": 8,
|
| 350 |
-
"start_s": 72.2,
|
| 351 |
"duration_s": 6.04,
|
| 352 |
"environment": "WebArena",
|
| 353 |
"task": "274",
|
|
@@ -389,13 +341,13 @@
|
|
| 389 |
"shown_arm": "edited",
|
| 390 |
"task_start_s": 0,
|
| 391 |
"task_end_s": 4.72369825001806,
|
| 392 |
-
"result_still_start_s":
|
| 393 |
"result_still_duration_s": 1.28,
|
| 394 |
"frame_clock": "capture timestamps"
|
| 395 |
},
|
| 396 |
{
|
| 397 |
-
"number":
|
| 398 |
-
"start_s":
|
| 399 |
"duration_s": 6.24,
|
| 400 |
"environment": "WebArena",
|
| 401 |
"task": "275",
|
|
@@ -437,13 +389,13 @@
|
|
| 437 |
"shown_arm": "edited",
|
| 438 |
"task_start_s": 0,
|
| 439 |
"task_end_s": 4.95540237496607,
|
| 440 |
-
"result_still_start_s":
|
| 441 |
"result_still_duration_s": 1.28,
|
| 442 |
"frame_clock": "capture timestamps"
|
| 443 |
},
|
| 444 |
{
|
| 445 |
-
"number":
|
| 446 |
-
"start_s":
|
| 447 |
"duration_s": 6.64,
|
| 448 |
"environment": "WebArena",
|
| 449 |
"task": "276",
|
|
@@ -485,13 +437,13 @@
|
|
| 485 |
"shown_arm": "edited",
|
| 486 |
"task_start_s": 0,
|
| 487 |
"task_end_s": 5.341348875081167,
|
| 488 |
-
"result_still_start_s":
|
| 489 |
"result_still_duration_s": 1.28,
|
| 490 |
"frame_clock": "capture timestamps"
|
| 491 |
},
|
| 492 |
{
|
| 493 |
-
"number":
|
| 494 |
-
"start_s":
|
| 495 |
"duration_s": 7.12,
|
| 496 |
"environment": "WebArena",
|
| 497 |
"task": "277",
|
|
@@ -533,13 +485,13 @@
|
|
| 533 |
"shown_arm": "edited",
|
| 534 |
"task_start_s": 0,
|
| 535 |
"task_end_s": 5.821562124998309,
|
| 536 |
-
"result_still_start_s":
|
| 537 |
"result_still_duration_s": 1.28,
|
| 538 |
"frame_clock": "capture timestamps"
|
| 539 |
},
|
| 540 |
{
|
| 541 |
-
"number":
|
| 542 |
-
"start_s":
|
| 543 |
"duration_s": 8.92,
|
| 544 |
"environment": "WebArena",
|
| 545 |
"task": "278",
|
|
@@ -581,13 +533,13 @@
|
|
| 581 |
"shown_arm": "edited",
|
| 582 |
"task_start_s": 0,
|
| 583 |
"task_end_s": 7.614025874994695,
|
| 584 |
-
"result_still_start_s":
|
| 585 |
"result_still_duration_s": 1.28,
|
| 586 |
"frame_clock": "capture timestamps"
|
| 587 |
},
|
| 588 |
{
|
| 589 |
-
"number":
|
| 590 |
-
"start_s":
|
| 591 |
"duration_s": 21.84,
|
| 592 |
"environment": "WebArena",
|
| 593 |
"task": "630",
|
|
@@ -627,10 +579,10 @@
|
|
| 627 |
"shown_arm": "edited",
|
| 628 |
"task_start_s": 0,
|
| 629 |
"task_end_s": 20.557142707984895,
|
| 630 |
-
"result_still_start_s":
|
| 631 |
"result_still_duration_s": 1.28,
|
| 632 |
"frame_clock": "capture timestamps"
|
| 633 |
}
|
| 634 |
],
|
| 635 |
-
"embedded_chapters":
|
| 636 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"sha256": "4918da3d8e665b12719749670f14ed21511ca1511fea261070292e6937f9c800",
|
| 3 |
"fps": 25,
|
| 4 |
"resolution": [
|
| 5 |
1200,
|
| 6 |
868
|
| 7 |
],
|
| 8 |
+
"duration_s": 98.08,
|
| 9 |
+
"task_count": 12,
|
| 10 |
+
"closing_start_s": 94.48,
|
| 11 |
"playback_rate": 1,
|
| 12 |
"display_labels": [
|
| 13 |
"Original weights",
|
| 14 |
"Edited weights"
|
| 15 |
],
|
| 16 |
+
"selection": "Selected demonstration tasks. One uninterrupted edited run per task at capture speed, followed by a labeled result still. Timings use the paired passing runs. The completed-order lookup uses the previously featured fastest take and appears once.",
|
| 17 |
"chapters": [
|
| 18 |
{
|
| 19 |
"number": 1,
|
|
|
|
| 300 |
{
|
| 301 |
"number": 7,
|
| 302 |
"start_s": 37.68,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 303 |
"duration_s": 6.04,
|
| 304 |
"environment": "WebArena",
|
| 305 |
"task": "274",
|
|
|
|
| 341 |
"shown_arm": "edited",
|
| 342 |
"task_start_s": 0,
|
| 343 |
"task_end_s": 4.72369825001806,
|
| 344 |
+
"result_still_start_s": 42.44,
|
| 345 |
"result_still_duration_s": 1.28,
|
| 346 |
"frame_clock": "capture timestamps"
|
| 347 |
},
|
| 348 |
{
|
| 349 |
+
"number": 8,
|
| 350 |
+
"start_s": 43.72,
|
| 351 |
"duration_s": 6.24,
|
| 352 |
"environment": "WebArena",
|
| 353 |
"task": "275",
|
|
|
|
| 389 |
"shown_arm": "edited",
|
| 390 |
"task_start_s": 0,
|
| 391 |
"task_end_s": 4.95540237496607,
|
| 392 |
+
"result_still_start_s": 48.68,
|
| 393 |
"result_still_duration_s": 1.28,
|
| 394 |
"frame_clock": "capture timestamps"
|
| 395 |
},
|
| 396 |
{
|
| 397 |
+
"number": 9,
|
| 398 |
+
"start_s": 49.96,
|
| 399 |
"duration_s": 6.64,
|
| 400 |
"environment": "WebArena",
|
| 401 |
"task": "276",
|
|
|
|
| 437 |
"shown_arm": "edited",
|
| 438 |
"task_start_s": 0,
|
| 439 |
"task_end_s": 5.341348875081167,
|
| 440 |
+
"result_still_start_s": 55.32,
|
| 441 |
"result_still_duration_s": 1.28,
|
| 442 |
"frame_clock": "capture timestamps"
|
| 443 |
},
|
| 444 |
{
|
| 445 |
+
"number": 10,
|
| 446 |
+
"start_s": 56.6,
|
| 447 |
"duration_s": 7.12,
|
| 448 |
"environment": "WebArena",
|
| 449 |
"task": "277",
|
|
|
|
| 485 |
"shown_arm": "edited",
|
| 486 |
"task_start_s": 0,
|
| 487 |
"task_end_s": 5.821562124998309,
|
| 488 |
+
"result_still_start_s": 62.44,
|
| 489 |
"result_still_duration_s": 1.28,
|
| 490 |
"frame_clock": "capture timestamps"
|
| 491 |
},
|
| 492 |
{
|
| 493 |
+
"number": 11,
|
| 494 |
+
"start_s": 63.72,
|
| 495 |
"duration_s": 8.92,
|
| 496 |
"environment": "WebArena",
|
| 497 |
"task": "278",
|
|
|
|
| 533 |
"shown_arm": "edited",
|
| 534 |
"task_start_s": 0,
|
| 535 |
"task_end_s": 7.614025874994695,
|
| 536 |
+
"result_still_start_s": 71.36,
|
| 537 |
"result_still_duration_s": 1.28,
|
| 538 |
"frame_clock": "capture timestamps"
|
| 539 |
},
|
| 540 |
{
|
| 541 |
+
"number": 12,
|
| 542 |
+
"start_s": 72.64,
|
| 543 |
"duration_s": 21.84,
|
| 544 |
"environment": "WebArena",
|
| 545 |
"task": "630",
|
|
|
|
| 579 |
"shown_arm": "edited",
|
| 580 |
"task_start_s": 0,
|
| 581 |
"task_end_s": 20.557142707984895,
|
| 582 |
+
"result_still_start_s": 93.2,
|
| 583 |
"result_still_duration_s": 1.28,
|
| 584 |
"frame_clock": "capture timestamps"
|
| 585 |
}
|
| 586 |
],
|
| 587 |
+
"embedded_chapters": 13
|
| 588 |
}
|
benchmark/speedups-film-receipts.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4042a68277a2344001c1094c9ffbb582b90b815d665aab4f31204b5981fd05e
|
| 3 |
+
size 38497
|
benchmark/speedups-timings.json
CHANGED
|
@@ -1,18 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"selection": "One uninterrupted edited run per task at capture speed, followed by a labeled result still. Timings use the paired passing runs. The completed-order lookup uses the previously featured fastest take and appears once.",
|
| 3 |
-
"tasks":
|
| 4 |
-
"mean_stock_s":
|
| 5 |
-
"mean_edit_s":
|
| 6 |
-
"time_speedup":
|
| 7 |
-
"time_saved_pct":
|
| 8 |
-
"film_sha256": "
|
| 9 |
-
"duration_s":
|
| 10 |
"release_checkpoint_sha256": "bbc639c4b54b0b748b011b9289512ccdce4c95298a4c19056d1b73a2a654e1d1",
|
| 11 |
"expanded_rtx": {
|
| 12 |
"tasks": [
|
| 13 |
275,
|
| 14 |
-
190
|
| 15 |
-
189
|
| 16 |
],
|
| 17 |
"pairs": [
|
| 18 |
{
|
|
@@ -111,104 +110,6 @@
|
|
| 111 |
"recording_sha256": "993a915623f7851110f0178c347bd5ae29ad90318f9e9c1c9ace7c0bf53aff2a"
|
| 112 |
}
|
| 113 |
},
|
| 114 |
-
{
|
| 115 |
-
"checkpoint": "search-submit-stop",
|
| 116 |
-
"task": 189,
|
| 117 |
-
"repeat": 1,
|
| 118 |
-
"order": [
|
| 119 |
-
"edited",
|
| 120 |
-
"original"
|
| 121 |
-
],
|
| 122 |
-
"site": "shopping",
|
| 123 |
-
"device": "RTX 5090",
|
| 124 |
-
"baseline": "Upstream stock",
|
| 125 |
-
"comparable": true,
|
| 126 |
-
"ratio": 1.962606911217544,
|
| 127 |
-
"original": {
|
| 128 |
-
"seconds": 6.104229875025339,
|
| 129 |
-
"score": 1.0,
|
| 130 |
-
"grader_status": "success",
|
| 131 |
-
"device": "RTX 5090",
|
| 132 |
-
"shard_sha256": "65e60f51aa1284d4fb022584908c315270334d991828bb774af60584523539d1",
|
| 133 |
-
"commands": [
|
| 134 |
-
"C1",
|
| 135 |
-
"C28",
|
| 136 |
-
"ANSWER [754.99]"
|
| 137 |
-
],
|
| 138 |
-
"generated": 620,
|
| 139 |
-
"thinking": 578,
|
| 140 |
-
"inference_seconds": 4.274760375148617,
|
| 141 |
-
"receipt_sha256": "c01c6c8aa792e1ae16983c2ad474b966f6c0fcf56558c5ff21edd1113d224e5e",
|
| 142 |
-
"recording_sha256": "fc244225b27a04d3f4141fc7041bad661ed2fc4d470cf21c1be67c2399a13d1e"
|
| 143 |
-
},
|
| 144 |
-
"edited": {
|
| 145 |
-
"seconds": 3.1102661669719964,
|
| 146 |
-
"score": 1.0,
|
| 147 |
-
"grader_status": "success",
|
| 148 |
-
"device": "RTX 5090",
|
| 149 |
-
"shard_sha256": "bbc639c4b54b0b748b011b9289512ccdce4c95298a4c19056d1b73a2a654e1d1",
|
| 150 |
-
"commands": [
|
| 151 |
-
"C1",
|
| 152 |
-
"C28",
|
| 153 |
-
"ANSWER [754.99]"
|
| 154 |
-
],
|
| 155 |
-
"generated": 22,
|
| 156 |
-
"thinking": 0,
|
| 157 |
-
"inference_seconds": 0.9284818329615518,
|
| 158 |
-
"receipt_sha256": "fbed2ebc713c45514796162f43130b9a237af33a75186cd5b7cc78c07c4974dc",
|
| 159 |
-
"recording_sha256": "8e630b90a7db5c4ce8fdd5a116c8f15edc558818d3768b3a1918e5ea093f8ed3"
|
| 160 |
-
}
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"checkpoint": "search-submit-stop",
|
| 164 |
-
"task": 189,
|
| 165 |
-
"repeat": 2,
|
| 166 |
-
"order": [
|
| 167 |
-
"original",
|
| 168 |
-
"edited"
|
| 169 |
-
],
|
| 170 |
-
"site": "shopping",
|
| 171 |
-
"device": "RTX 5090",
|
| 172 |
-
"baseline": "Upstream stock",
|
| 173 |
-
"comparable": true,
|
| 174 |
-
"ratio": 0.905024135016417,
|
| 175 |
-
"original": {
|
| 176 |
-
"seconds": 6.321594374952838,
|
| 177 |
-
"score": 1.0,
|
| 178 |
-
"grader_status": "success",
|
| 179 |
-
"device": "RTX 5090",
|
| 180 |
-
"shard_sha256": "65e60f51aa1284d4fb022584908c315270334d991828bb774af60584523539d1",
|
| 181 |
-
"commands": [
|
| 182 |
-
"C1",
|
| 183 |
-
"C28",
|
| 184 |
-
"ANSWER [754.99]"
|
| 185 |
-
],
|
| 186 |
-
"generated": 620,
|
| 187 |
-
"thinking": 578,
|
| 188 |
-
"inference_seconds": 4.289602998876944,
|
| 189 |
-
"receipt_sha256": "dba8c17ed02c10d7e6039ed0c0c57bf2a4e140fa88433e6fefbfbf18ac996bb4",
|
| 190 |
-
"recording_sha256": "4fc5007af77648d75306ee701cf48b69edc2f07e8903e8a6fba553ff1c3e39c7"
|
| 191 |
-
},
|
| 192 |
-
"edited": {
|
| 193 |
-
"seconds": 6.985000874963589,
|
| 194 |
-
"score": 1.0,
|
| 195 |
-
"grader_status": "success",
|
| 196 |
-
"device": "RTX 5090",
|
| 197 |
-
"shard_sha256": "bbc639c4b54b0b748b011b9289512ccdce4c95298a4c19056d1b73a2a654e1d1",
|
| 198 |
-
"commands": [
|
| 199 |
-
"C1",
|
| 200 |
-
"C1",
|
| 201 |
-
"C28",
|
| 202 |
-
"",
|
| 203 |
-
"ANSWER [754.99]"
|
| 204 |
-
],
|
| 205 |
-
"generated": 543,
|
| 206 |
-
"thinking": 510,
|
| 207 |
-
"inference_seconds": 4.45032141613774,
|
| 208 |
-
"receipt_sha256": "04b717751d83fc591366f766bd3cf853a8d254f7212f48b4ea00b0644247b5eb",
|
| 209 |
-
"recording_sha256": "3f88cf0b7c3cb68b8f77cbb4cad6eacecaa26d443eca928d72b4ec2ac4245485"
|
| 210 |
-
}
|
| 211 |
-
},
|
| 212 |
{
|
| 213 |
"checkpoint": "search-submit-stop",
|
| 214 |
"task": 190,
|
|
@@ -307,9 +208,9 @@
|
|
| 307 |
}
|
| 308 |
}
|
| 309 |
],
|
| 310 |
-
"mean_stock_s": 6.
|
| 311 |
-
"mean_edit_s":
|
| 312 |
-
"time_speedup":
|
| 313 |
},
|
| 314 |
"mac_xbox": [
|
| 315 |
{
|
|
@@ -413,5 +314,5 @@
|
|
| 413 |
}
|
| 414 |
}
|
| 415 |
],
|
| 416 |
-
"all_run_evidence": "https://github.com/jtc268/inkling-2-fast-computer-use/blob/
|
| 417 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"selection": "Selected demonstration tasks. One uninterrupted edited run per task at capture speed, followed by a labeled result still. Timings use the paired passing runs. The completed-order lookup uses the previously featured fastest take and appears once.",
|
| 3 |
+
"tasks": 12,
|
| 4 |
+
"mean_stock_s": 20.758587340348942,
|
| 5 |
+
"mean_edit_s": 6.5751733922516,
|
| 6 |
+
"time_speedup": 3.1571163377701255,
|
| 7 |
+
"time_saved_pct": 68.32552579591346,
|
| 8 |
+
"film_sha256": "4918da3d8e665b12719749670f14ed21511ca1511fea261070292e6937f9c800",
|
| 9 |
+
"duration_s": 98.08,
|
| 10 |
"release_checkpoint_sha256": "bbc639c4b54b0b748b011b9289512ccdce4c95298a4c19056d1b73a2a654e1d1",
|
| 11 |
"expanded_rtx": {
|
| 12 |
"tasks": [
|
| 13 |
275,
|
| 14 |
+
190
|
|
|
|
| 15 |
],
|
| 16 |
"pairs": [
|
| 17 |
{
|
|
|
|
| 110 |
"recording_sha256": "993a915623f7851110f0178c347bd5ae29ad90318f9e9c1c9ace7c0bf53aff2a"
|
| 111 |
}
|
| 112 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
{
|
| 114 |
"checkpoint": "search-submit-stop",
|
| 115 |
"task": 190,
|
|
|
|
| 208 |
}
|
| 209 |
}
|
| 210 |
],
|
| 211 |
+
"mean_stock_s": 6.098677093774313,
|
| 212 |
+
"mean_edit_s": 2.9726315830193926,
|
| 213 |
+
"time_speedup": 2.0516087928998252
|
| 214 |
},
|
| 215 |
"mac_xbox": [
|
| 216 |
{
|
|
|
|
| 314 |
}
|
| 315 |
}
|
| 316 |
],
|
| 317 |
+
"all_run_evidence": "https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/WEBARENA-ORDER-CHECKPOINTS.md"
|
| 318 |
}
|