{
  "source_model": "tinnel123/OmniJev",
  "source_revision": "v1.1",
  "source_release": "OmniJev-4B-ckpt",
  "backbone": "Qwen/Qwen3.5-4B",
  "operation": "merge official LoRA adapter into the backbone in bfloat16, then convert the fused backbone to MLX affine quantization",
  "bits": 5,
  "group_size": 64,
  "quantization_mode": "affine",
  "vision_precision": "bfloat16",
  "decision_head": "official head.pt exported to decision_head/head.npz",
  "decision_head_precision": "float32",
  "new_training": false,
  "local_validation": {
    "benchmark": "ScienceQA visual subset",
    "questions": 50,
    "max_pixels": 87808,
    "correct": 44,
    "accuracy": 0.88,
    "warm_median_ms": 737.4855829984881,
    "warm_p95_ms": 1012.7517079818062,
    "hardware": "Mac mini M4, 16 GB unified memory"
  }
}