{
  "architectures": [
    "AlpaJudgeRF"
  ],
  "backbone_kind": "alpamayo1",
  "backbone_native_camera_policy": {
    "frame_label": "frame_num",
    "include_camera_ids": true,
    "token_layout": "camera_ts"
  },
  "backbone_native_pixel_policy": {
    "max_pixels": 196608,
    "min_pixels": 163840
  },
  "backbone_source_config_sha256": "4b3933e89063c79431fbda26d8f27e645c660b2fb51c52ee15d765e3e579678f",
  "backbone_vlm_config_sha256": "f1043e53e344583304960e52b94a19953e39a034759eeff725ae7937ca792f5a",
  "dtype": "bfloat16",
  "freeze_vision": true,
  "head_pool_tokens": 1,
  "hidden_size": 2048,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4
  },
  "max_length": 4096,
  "max_pixels": 196608,
  "min_pixels": 163840,
  "model_type": "alpajudge_rf",
  "overall_score_loss_weight": 0.0,
  "padding_side": "left",
  "prompt_contract_sha256": "15474783891270646f087b4642f11565b0f42c7e5df697c6759c9f35b2615706",
  "prompt_mode": "compact_scoring",
  "prompt_policy": "fixed_compact_scoring_instruction",
  "rubric_prompt": "",
  "score_contract": "vlm_rubric_c24f80fa_v1_no_direction_quality_diagnostic",
  "score_mode": "subscores",
  "student_prompt_sha256": "45994171c437907a24751a79cf4980492ddca1dfdf1eceb579eeec9d4487dbb2",
  "subscore_label_smoothing": null,
  "subscore_loss_weights": null,
  "teacher_prompt_sha256": "c24f80fa6ae3ca406088cad238941378a037149d205c7c91a46fdb48f788dbf3",
  "transformers_version": "4.57.6",
  "vlm_config": {
    "_name_or_path": "Qwen/Qwen3-VL-2B-Instruct",
    "architectures": [
      "Qwen3VLForConditionalGeneration"
    ],
    "dtype": "bfloat16",
    "image_token_id": 151655,
    "model_type": "qwen3_vl",
    "text_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "attention_bias": false,
      "attention_dropout": 0.0,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": 151643,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "dtype": "bfloat16",
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": 151645,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "head_dim": 128,
      "hidden_act": "silu",
      "hidden_size": 2048,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_range": 0.02,
      "intermediate_size": 6144,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "length_penalty": 1.0,
      "max_length": 20,
      "max_position_embeddings": 262144,
      "min_length": 0,
      "model_type": "qwen3_vl_text",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 16,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_hidden_layers": 28,
      "num_key_value_heads": 8,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "prefix": null,
      "problem_type": null,
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "rms_norm_eps": 1e-06,
      "rope_scaling": {
        "mrope_interleaved": true,
        "mrope_section": [
          24,
          20,
          20
        ],
        "rope_type": "default"
      },
      "rope_theta": 5000000,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torchscript": false,
      "typical_p": 1.0,
      "use_bfloat16": false,
      "use_cache": true,
      "vocab_size": 155776
    },
    "tie_word_embeddings": true,
    "video_token_id": 151656,
    "vision_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "deepstack_visual_indexes": [
        5,
        11,
        17
      ],
      "depth": 24,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "dtype": "bfloat16",
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_act": "gelu_pytorch_tanh",
      "hidden_size": 1024,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "in_channels": 3,
      "initializer_range": 0.02,
      "intermediate_size": 4096,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "qwen3_vl",
      "no_repeat_ngram_size": 0,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_heads": 16,
      "num_position_embeddings": 2304,
      "num_return_sequences": 1,
      "out_hidden_size": 2048,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "patch_size": 16,
      "prefix": null,
      "problem_type": null,
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "spatial_merge_size": 2,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "temporal_patch_size": 2,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torchscript": false,
      "typical_p": 1.0,
      "use_bfloat16": false
    },
    "vision_end_token_id": 151653,
    "vision_start_token_id": 151652
  }
}