mirror of
https://github.com/hanzoai/trolley-bench.git
synced 2026-10-30 15:00:49 +00:00
* Removed the stale publication-status comment without changing the frozen analysis plan * Kept the original checksum verifiable after removing that comment * Repackaged local command paths and removed operator attribution to keep the working environment out of the public files * Rebuilt site references from their sources without changing any prompt, answer or measurement
246 lines
8.2 KiB
JSON
246 lines
8.2 KiB
JSON
{
|
|
"model_id": "strands-decider-2b",
|
|
"code": {
|
|
"repo": "https://github.com/strands-labs/strands-decider",
|
|
"commit": "fe39fad9ec8ec355993f76b977348d915ec9cb65"
|
|
},
|
|
"runtime": "Strands Decider 2B (hobson-v19): strands-decider serve (PyPI 0.1.0 = strands-labs/strands-decider@fe39fad), PyTorch MPS, bfloat16 as configured (hobson_config.json), LoRA adapter and pointer head on Qwen3.5-2B-Base; native Noul, all questions in one call",
|
|
"server_command": [
|
|
"<scratch>/strands/venv-strands/bin/strands-decider",
|
|
"serve",
|
|
"<scratch>/strands/hf/hub/models--StrandsAgents--strands-decider-2B-hobson-v19/snapshots/bb282d786bc251fd4e3068de3ada9ddbb38127cd",
|
|
"--host",
|
|
"127.0.0.1",
|
|
"--port",
|
|
"8016",
|
|
"--device",
|
|
"mps"
|
|
],
|
|
"startup_s_including_download": 6,
|
|
"probe_answer": {
|
|
"model": "bb282d786bc251fd4e3068de3ada9ddbb38127cd",
|
|
"answers": {
|
|
"q": {
|
|
"type": "noul",
|
|
"noul": 0.9125
|
|
}
|
|
},
|
|
"usage": {
|
|
"input_tokens": 79,
|
|
"output_tokens": 1
|
|
},
|
|
"latency_ms": 716.33
|
|
},
|
|
"weights": [
|
|
{
|
|
"repo": "Qwen/Qwen3.5-2B-Base",
|
|
"revision": "b1485b2fa6dfa1287294f269f5fb618e03d52d7c",
|
|
"bytes": 4571206192,
|
|
"files": {
|
|
".gitattributes": {
|
|
"sha256": "34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930",
|
|
"bytes": 1570
|
|
},
|
|
"LICENSE": {
|
|
"sha256": "50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32",
|
|
"bytes": 11343
|
|
},
|
|
"README.md": {
|
|
"sha256": "50ca45b87d976d9850de95ad00e76fba77e105c2cdef1093b8e3bb261d9a1787",
|
|
"bytes": 3721
|
|
},
|
|
"config.json": {
|
|
"sha256": "ed1c1723241f23f7f4e23430759cbd7dcfb4103cbdfe052bfe7626b57c2615b4",
|
|
"bytes": 2908
|
|
},
|
|
"merges.txt": {
|
|
"sha256": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d",
|
|
"bytes": 3353259
|
|
},
|
|
"model.safetensors-00001-of-00001.safetensors": {
|
|
"sha256": "6cb808828f2829da873eb9e83ef220d632e340d54272f0ebdd1a31bd8ee0ded2",
|
|
"bytes": 4548221488
|
|
},
|
|
"model.safetensors.index.json": {
|
|
"sha256": "74d2ddfe79f10f35b27b498632f02b97b60dd9ec39b35d7c5a890c399284e319",
|
|
"bytes": 64460
|
|
},
|
|
"preprocessor_config.json": {
|
|
"sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
|
|
"bytes": 390
|
|
},
|
|
"tokenizer.json": {
|
|
"sha256": "59036b7ec9c1c130de9dd3716f37308a51038389ae6fb9ba62e87c246696707a",
|
|
"bytes": 12807196
|
|
},
|
|
"tokenizer_config.json": {
|
|
"sha256": "e611fbccc7c29ef3b1cafb1cb7ea548d189968632901d678fd62be68c47885de",
|
|
"bytes": 16712
|
|
},
|
|
"video_preprocessor_config.json": {
|
|
"sha256": "d039cd7d88b3502a99edd455496b75b44ecf7dd3b3669748bafac37e6cecc085",
|
|
"bytes": 386
|
|
},
|
|
"vocab.json": {
|
|
"sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003",
|
|
"bytes": 6722759
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"repo": "StrandsAgents/strands-decider-2B-hobson-v19",
|
|
"revision": "bb282d786bc251fd4e3068de3ada9ddbb38127cd",
|
|
"bytes": 92078245,
|
|
"files": {
|
|
".gitattributes": {
|
|
"sha256": "34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930",
|
|
"bytes": 1570
|
|
},
|
|
"LICENSE.md": {
|
|
"sha256": "95e36511c33366a2105047cae24c04a60f09c4c755662050986eaf5547bf6fe9",
|
|
"bytes": 13079
|
|
},
|
|
"MANIFEST.sha256": {
|
|
"sha256": "0d006e9254ed218a4f1a68ebf41520dd30f8327838262acfb47e05f435b753c3",
|
|
"bytes": 3256
|
|
},
|
|
"README.md": {
|
|
"sha256": "e9bd6ec77988cf45a0b13ebf3193743bcf1c9a0bd34f43bed84a211c76025ecb",
|
|
"bytes": 9841
|
|
},
|
|
"chat_template.jinja": {
|
|
"sha256": "273d8e0e683b885071fb17e08d71e5f2a5ddfb5309756181681de4f5a1822d80",
|
|
"bytes": 7755
|
|
},
|
|
"eval/internal/adequacy_gen_eval.rows.json": {
|
|
"sha256": "2bf7cdc629d95f91d550d73424b2f8b8a9ebcf21930fa5d1159e51bb0e2144e3",
|
|
"bytes": 1873
|
|
},
|
|
"eval/internal/adequacy_hs2_eval.rows.json": {
|
|
"sha256": "564095cebcf13a133c45c73d2a15c6a573563a0f431401d8ad48b0f624d6b689",
|
|
"bytes": 1469
|
|
},
|
|
"eval/internal/eval.log": {
|
|
"sha256": "7ec9734bbadd05e64e11385089f3494ff50c59aee6968fd90ac0338e98ebc65c",
|
|
"bytes": 6853
|
|
},
|
|
"eval/internal/recipe_heldout.json": {
|
|
"sha256": "205a511101512f27142999f4139e2bb99c3f6df2caee32c7126eb0cd09192878",
|
|
"bytes": 2478
|
|
},
|
|
"eval/jevbench-w3072/health.json": {
|
|
"sha256": "4f8fc325572c04be2e15de1b9c7056b3b5c98dc5778d2bdb87b322bd965cd60c",
|
|
"bytes": 263
|
|
},
|
|
"eval/jevbench-w3072/manifest.json": {
|
|
"sha256": "2e3cc118e64905dd40f16b4928981506e705bbfd8f72bce2ca75c36d5b4ade49",
|
|
"bytes": 505
|
|
},
|
|
"eval/jevbench-w3072/paired.json": {
|
|
"sha256": "ff5f7ac1a200ac7af5f643da9303a0bce216eb1490dcd331acfaa5fddfc89593",
|
|
"bytes": 1785
|
|
},
|
|
"eval/jevbench-w3072/paired.txt": {
|
|
"sha256": "e7047829d1bf26cd7c052ffa4dfad2fc3d8f4dec65c21cb50997935dd662de18",
|
|
"bytes": 1185
|
|
},
|
|
"eval/jevbench-w3072/results.jsonl": {
|
|
"sha256": "bd020215d36273463dc76d0c541873483c1f822fb211a84d4728d26d700ef715",
|
|
"bytes": 177333
|
|
},
|
|
"eval/jevbench-w3072/run_meta.json": {
|
|
"sha256": "8b611d30e1e94505e950e368af13b957c00d041af2bef2317a8d4cd4cd2d5602",
|
|
"bytes": 952
|
|
},
|
|
"eval/jevbench-w3072/summary.json": {
|
|
"sha256": "8c77fb5a0f6156052c18c60f56ef9f1adc84db265ba7ce1859f278d6b9b5969e",
|
|
"bytes": 47048
|
|
},
|
|
"eval/jevbench-w4096/health.json": {
|
|
"sha256": "0a4ad7bc2017d90f96e6246c47e7c0fd97681709121ed9d607bb59b0ee4591f5",
|
|
"bytes": 257
|
|
},
|
|
"eval/jevbench-w4096/manifest.json": {
|
|
"sha256": "56aec996cd7526d579e990d0f10a0c0d783992df4033d22bc5b438d59108be42",
|
|
"bytes": 493
|
|
},
|
|
"eval/jevbench-w4096/paired.json": {
|
|
"sha256": "319329f08e1a3c6885fbe0984f1ab50f7ec66c128f6e33072b31ccc9f3f8784b",
|
|
"bytes": 1785
|
|
},
|
|
"eval/jevbench-w4096/paired.txt": {
|
|
"sha256": "0864ac86efe784daa9401c53b83cd2e81271468be43050e5e60a6ed4d7c18607",
|
|
"bytes": 1185
|
|
},
|
|
"eval/jevbench-w4096/results.jsonl": {
|
|
"sha256": "67519947e87c95717892931da4a4774ff77b2ed6f175373e06abe7624781dd08",
|
|
"bytes": 177362
|
|
},
|
|
"eval/jevbench-w4096/run_meta.json": {
|
|
"sha256": "c8b790dcae49ff081cc52c5261fdcb765aaaf2c13ff87a8c67263c5cdd2426da",
|
|
"bytes": 946
|
|
},
|
|
"eval/jevbench-w4096/summary.json": {
|
|
"sha256": "67cbaf93b182869abd656583e873e3e1761866c03910daa7e252b5bc690e16a0",
|
|
"bytes": 47095
|
|
},
|
|
"eval/summary.json": {
|
|
"sha256": "581a5cbd31f142c00a282d21f7d9a2603a66b4f07fc11dcca9e7b32ff0a3f169",
|
|
"bytes": 3787
|
|
},
|
|
"head.safetensors": {
|
|
"sha256": "d82c6ff36bcec6a279d41aa06eaddc2d050a2eb73e966fceec93dfff6e6440e3",
|
|
"bytes": 4213224
|
|
},
|
|
"history.json": {
|
|
"sha256": "a30496e55bf78788094ac95297e49411a3533a495e4664507bd7e9bdd7877b6e",
|
|
"bytes": 24405
|
|
},
|
|
"hobson_config.json": {
|
|
"sha256": "2ae86f2ed56975f68e8f2f368104df8ce0ff4b7d9d146dcaf8eec5626d62449d",
|
|
"bytes": 743
|
|
},
|
|
"lora/adapter_config.json": {
|
|
"sha256": "eb48e4ff81569664c4dd2a504b53da598eeaa390c265c2269ce4fe7526eab38a",
|
|
"bytes": 1271
|
|
},
|
|
"lora/adapter_model.safetensors": {
|
|
"sha256": "1b57bbfb96e0b79ea9bab8734e46444a1c12884246eea4b45751029d724d66a6",
|
|
"bytes": 67324872
|
|
},
|
|
"provenance.json": {
|
|
"sha256": "eb9ab7e029d9cc6718a6302a3edc6085bbb42c4ee42284b8ee7727f0ab4416a1",
|
|
"bytes": 970
|
|
},
|
|
"tokenizer.json": {
|
|
"sha256": "d3aa2a0e5f04237c1d3b754b1deea09704924f97511aed36aa20f510a97555d8",
|
|
"bytes": 19989592
|
|
},
|
|
"tokenizer_config.json": {
|
|
"sha256": "8671bed7c852ce9e661be94f179a7b4ffd091c2a65aea0363e5501c20318ee45",
|
|
"bytes": 1128
|
|
},
|
|
"train_config.json": {
|
|
"sha256": "5d15c863a3b83103d4d59068a8341b61745b10079d6f8509fab537415d1eb31e",
|
|
"bytes": 1465
|
|
},
|
|
"training/configs/train-parent.yaml": {
|
|
"sha256": "02db9272914ab210264fc515dd7905d4890d2190e0982f40e04d251ad655da81",
|
|
"bytes": 2286
|
|
},
|
|
"training/configs/train.yaml": {
|
|
"sha256": "daf877b9fb0347410e7688ef17d3004efa8353f455d779f84d00055e4faf3ee7",
|
|
"bytes": 3693
|
|
},
|
|
"training/data_sha256.txt": {
|
|
"sha256": "46412da746419587e68891679c65c94f5d0f7bab246b54d76719578273579169",
|
|
"bytes": 1907
|
|
},
|
|
"training/stages.jsonl": {
|
|
"sha256": "c6d182882d57ee619e60ffcadfc3ee8a6c45ce48052cc0e35615e5bbd61b6aa1",
|
|
"bytes": 2534
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |