{
 "name": "Wald-Q4B v2.1",
 "repo": "org2ai/Wald-4B",
 "revision": "v2.1",
 "checkpoint": "056A0-c31",
 "parent_checkpoint": null,
 "base_model": "Qwen/Qwen3.5-4B",
 "base_revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
 "license": "apache-2.0",
 "parameters": "4B",
 "dtype": "bfloat16",
 "model_files": {
  "chat_template.jinja": {
   "sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
   "bytes": 7756
  },
  "config.json": {
   "sha256": "ddc63e1c717afa86c865bb5e01313d89d72bb53b97ad4a8a03ba8510c0621670",
   "bytes": 3161
  },
  "generation_config.json": {
   "sha256": "62153eb6c69f2e1f426beaa8002b7186437e949c7588167085df14e10e9c0a73",
   "bytes": 116
  },
  "merges.txt": {
   "sha256": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d",
   "bytes": 3353259
  },
  "model-00001-of-00003.safetensors": {
   "sha256": "1bf33f0d7f7722ae8f87bca21a9d5ebca8328962e6b170abd09d354d2c978a57",
   "bytes": 4757977272
  },
  "model-00002-of-00003.safetensors": {
   "sha256": "7cccb8e4ea4c9858c8c78754bee789f5ccc8b437836b307c7919a15165097aef",
   "bytes": 3653581040
  },
  "model-00003-of-00003.safetensors": {
   "sha256": "9a8340e453e63f70185e56fde60aeae26085fe3c39e20ac1662b4325f01a78eb",
   "bytes": 908262184
  },
  "model.safetensors.index.json": {
   "sha256": "6db63a968a513eb0693feee5ccbc440cbbee43c6b644c0bd33e880ca7d0b54b3",
   "bytes": 67340
  },
  "preprocessor_config.json": {
   "sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
   "bytes": 390
  },
  "tokenizer.json": {
   "sha256": "bd53432f0de26d67a83b634040d4f043053da4ecd0c759e7f4b24ad4f8bb9a81",
   "bytes": 19989509
  },
  "tokenizer_config.json": {
   "sha256": "bee8eba30f0eb4af73c0fe2cd06d0f89b657d7819941c438157ec42f7c80ea87",
   "bytes": 1123
  },
  "video_preprocessor_config.json": {
   "sha256": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13",
   "bytes": 385
  },
  "vocab.json": {
   "sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003",
   "bytes": 6722759
  },
  "graft-manifest.json": {
   "sha256": "4de700a433f11dd89ae29bf617722a96d4469d9e3b3dbff3ddd0faf450ffe442",
   "bytes": 113687
  },
  "graft-report.json": {
   "sha256": "9e6e9ab73a5b73006b815206cb5f8a5d8e4c64e8c07f1bdd4acef1f96c5b9072",
   "bytes": 765
  },
  "SHA256SUMS": {
   "sha256": "1ba76d9616233fc4f347859c07c9359492aaa5e45bf5f2f1fb8ce43df3cce4ad",
   "bytes": 1326
  }
 },
 "serving": {
  "engine": "native-v2-vision",
  "checkpoint": "04701-c22",
  "variant": "vision: 04701-c22 language model (426 tensors, byte-identical) + Qwen/Qwen3.5-4B@851bf6e8 chat vision tower (297) + chat MTP head (15) = 738 keys; Qwen3_5ForConditionalGeneration",
  "model_sha256": "6ae382f5a0ed9f4c53cd0953cb9606b1627a6816350340a59114860e6cf6f29a",
  "effort": "auto",
  "prompt_format": "repeat_state_plain",
  "max_model_len": 131072,
  "thought_budget": 512,
  "temperature": "temperature.json",
  "temperature_sha256": "a0f72cd2d0a653e81051e5a0c77fc1a69131552a8102b580a93a6dbe7908b2da",
  "vision": {
   "server": "wald-serve-native-vision",
   "image_prompt_format": "plain",
   "max_images": 16,
   "vllm_args": [
    "--limit-mm-per-prompt",
    "{\"image\": 16, \"video\": 0}",
    "--mm-processor-kwargs",
    "{\"size\": {\"shortest_edge\": 65536, \"longest_edge\": 1048576}}",
    "--trust-request-chat-template"
   ]
  },
  "vllm": {
   "version": "0.30.0",
   "transformers": "5.17.0",
   "args": [
    "--max-model-len",
    "131072",
    "--gpu-memory-utilization",
    "0.85",
    "--max-num-seqs",
    "128",
    "--seed",
    "0"
   ],
   "env": {
    "VLLM_USE_FLASHINFER_SAMPLER": "0"
   }
  }
 },
 "training": "one full-parameter pass of decision training on corpus c31 from Qwen/Qwen3.5-4B chat (state-KL 0.05 to the base); released weights = 0.85 x trained (05600-c31) + 0.15 x base (WiSE)",
 "evaluation": {
  "policies_measured": [
   "onepass",
   "auto0.7"
  ],
  "di03_public_auto": {
   "value": 54.18,
   "balanced_raw": 65.65,
   "breadth_skill": 52.45,
   "requests": 140620,
   "scoreable": 140178,
   "excluded": 442,
   "errors": 0,
   "areas": {
    "knowledge": 0.412,
    "language": 0.598,
    "retrieval": 0.528,
    "tools": 0.793,
    "arts": 0.301
   },
   "gsm8k": 0.876,
   "requests_with_thought": 0.402,
   "source": "results/c16d-di03-full-1008/README.md + official-CPU-scores/"
  },
  "rows": [
   {
    "en": "Decision Index 0.3, complete public suite",
    "zh": "",
    "onepass": "not run",
    "auto0.7": "**54.18** (our full run)",
    "jev": "57.96 (board public column)"
   },
   {
    "en": "JevBench public set (231)",
    "zh": "",
    "onepass": "204/231",
    "auto0.7": "**210/231**",
    "jev": "200/231"
   },
   {
    "en": "JevBench-XL TEST (8,177)",
    "zh": "",
    "onepass": "65.20 %",
    "auto0.7": "**65.78 %**",
    "jev": "67.85 %"
   }
  ],
  "latency": {
   "requests": 750,
   "warmup": 10,
   "gpu": "NVIDIA RTX PRO 6000 Blackwell (96 GB)",
   "auto_median_ms": 147.9,
   "auto_mean_ms": 478.0,
   "auto_p80_ms": 532.4,
   "auto_thought_share": 0.3307,
   "onepass_median_ms": 41.9,
   "onepass_mean_ms": 110.2,
   "weights": "the release graft without its unused MTP head (same language-model and vision tensors; the MTP head only acts under speculative decoding, which is off)",
   "source": "results/wald4b-v2-release/latency-pro6000-750.json",
   "rtx5090_same_read": {
    "auto_median_ms": 202.9,
    "onepass_median_ms": 71.3,
    "weights": "release graft incl. MTP"
   }
  },
  "not_measured": [
   "Always 512 policy",
   "DI 0.2.1 sample",
   "multistep_decisions",
   "XL calibration (ECE)"
  ]
 },
 "previous_releases": {
  "v1.2": "02600-f19",
  "v1.1": "022D0-f7",
  "v1.0": "021A0-f10"
 },
 "training_data_note": "Includes synthetic data generated and/or labelled by large frontier models; see PROVENANCE.md.",
 "submitted": false
}