{
  "architectures": [
    "DVLAForActionPrediction"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "DAMO-NLP-SG/VideoLLaMA3-7B-Image--configuration_videollama3.Videollama3Qwen2Config",
    "AutoModelForCausalLM": "DAMO-NLP-SG/VideoLLaMA3-7B-Image--modeling_videollama3.Videollama3Qwen2ForCausalLM"
  },
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_token_index": 151665,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "mm_projector_type": "mlp2x_gelu",
  "model_type": "dvla",
  "n_action_bins": 256,
  "norm_stats": {
    "bridge_orig": {
      "action": {
        "mask": [
          true,
          true,
          true,
          true,
          true,
          true,
          false
        ],
        "max": [
          0.41691166162490845,
          0.25864794850349426,
          0.21218234300613403,
          3.122201919555664,
          1.8618112802505493,
          6.272472858428955,
          1.0
        ],
        "mean": [
          0.00023162984871305525,
          0.00013371460954658687,
          -0.00013210502220317721,
          -0.00014224917686078697,
          -0.0003957618318963796,
          0.00025795758119784296,
          0.5765169858932495
        ],
        "min": [
          -0.4007510244846344,
          -0.12928041815757751,
          -0.22553899884223938,
          -3.2010786533355713,
          -1.8618112802505493,
          -6.279075622558594,
          0.0
        ],
        "q01": [
          -0.028744795620441438,
          -0.041743524745106696,
          -0.02612247958779335,
          -0.08074554242193699,
          -0.09273611158132553,
          -0.20663773745298386,
          0.0
        ],
        "q99": [
          0.028299489319324488,
          0.04087499871850013,
          0.040158278569579056,
          0.08191050931811326,
          0.07803218640387051,
          0.2031656354665755,
          1.0
        ],
        "std": [
          0.009774772450327873,
          0.013701396994292736,
          0.012669386342167854,
          0.02856358513236046,
          0.03065265156328678,
          0.07559732347726822,
          0.4959997236728668
        ]
      },
      "num_trajectories": 48624,
      "num_transitions": 1728258,
      "proprio": {
        "max": [
          0.5735528469085693,
          0.4034728705883026,
          0.36494991183280945,
          1.3517684936523438,
          1.570796251296997,
          3.141204357147217,
          0.0,
          1.1121242046356201
        ],
        "mean": [
          0.30948513746261597,
          0.030666163191199303,
          0.06444736570119858,
          0.0068027242086827755,
          -0.07731744647026062,
          0.10813789069652557,
          0.0,
          0.7086173892021179
        ],
        "min": [
          -0.04167502000927925,
          -0.3945816159248352,
          -0.15537554025650024,
          -3.141592502593994,
          -1.4992541074752808,
          -3.14153790473938,
          0.0,
          0.04637829214334488
        ],
        "q01": [
          0.17092366471886636,
          -0.17033958569169044,
          -0.05617850091308355,
          -0.3667951425909996,
          -0.5440364676713944,
          -1.3451742899417878,
          0.0,
          0.052190229296684265
        ],
        "q99": [
          0.45397736728191357,
          0.23543687969446145,
          0.19510107412934283,
          0.3818274670839303,
          0.2794133839011189,
          1.8331137096881818,
          0.0,
          1.0105689764022827
        ],
        "std": [
          0.06067129969596863,
          0.09202422946691513,
          0.0516839325428009,
          0.13189035654067993,
          0.1705130785703659,
          0.5743006467819214,
          0.0,
          0.3522878885269165
        ]
      }
    },
    "fractal20220817_data": {
      "action": {
        "mask": [
          true,
          true,
          true,
          true,
          true,
          true,
          false
        ],
        "max": [
          2.9984593391418457,
          22.09052848815918,
          2.7507524490356445,
          1.570636510848999,
          1.5321086645126343,
          1.5691522359848022,
          1.0
        ],
        "mean": [
          0.0070160930044949055,
          0.006287453696131706,
          -0.012577778659760952,
          0.04329700767993927,
          -0.005719248205423355,
          0.0009455775725655258,
          0.535513699054718
        ],
        "min": [
          -2.0204520225524902,
          -5.497899532318115,
          -2.031663417816162,
          -1.569917917251587,
          -1.569892168045044,
          -1.570419430732727,
          0.0
        ],
        "q01": [
          -0.22409614741802214,
          -0.14817706286907195,
          -0.2316769856214523,
          -0.3531744807958603,
          -0.4192173588275909,
          -0.4368023717403412,
          0.0
        ],
        "q99": [
          0.17836674451827994,
          0.14942033141851413,
          0.21879618436098075,
          0.5897578334808342,
          0.35292886614799457,
          0.4487913608551022,
          1.0
        ],
        "std": [
          0.0693204402923584,
          0.060718413442373276,
          0.07362836599349976,
          0.15637660026550293,
          0.13175784051418304,
          0.146182581782341,
          0.4972381293773651
        ]
      },
      "num_trajectories": 78480,
      "num_transitions": 3404867,
      "proprio": {
        "max": [
          1.0534898042678833,
          0.48018959164619446,
          1.6896663904190063,
          0.9999993443489075,
          0.9999874830245972,
          0.9554369449615479,
          0.9914546012878418,
          1.0
        ],
        "mean": [
          0.5597754120826721,
          -0.0832320973277092,
          0.7760888934135437,
          -0.24704332649707794,
          0.49434685707092285,
          0.09261937439441681,
          0.20921756327152252,
          0.42606088519096375
        ],
        "min": [
          -0.4436439275741577,
          -0.9970501065254211,
          -0.006579156965017319,
          -0.8643477559089661,
          -0.7079970240592957,
          -0.7688722014427185,
          -0.4999994933605194,
          0.0
        ],
        "q01": [
          0.32485780119895935,
          -0.2830313414335251,
          0.14108185589313507,
          -0.6863587307929992,
          -0.6807721078395843,
          -0.36089446604251857,
          -0.4545843780040741,
          0.0
        ],
        "q99": [
          0.8753369486331939,
          0.21245125174522383,
          1.072377111911773,
          0.9382593035697933,
          0.9568788063526152,
          0.4598054605722425,
          0.7213053238391873,
          1.0
        ],
        "std": [
          0.12438706308603287,
          0.1155894473195076,
          0.24558264017105103,
          0.5133047699928284,
          0.522326648235321,
          0.16654427349567413,
          0.27579590678215027,
          0.4560266435146332
        ]
      }
    }
  },
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "pad_to_multiple_of": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.50.3",
  "use_cache": false,
  "use_sliding_window": false,
  "use_token_compression": false,
  "vision_encoder": "videollamae3vision_encoder",
  "vision_encoder_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "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,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "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": 1152,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "intermediate_size": 4304,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "videollama3_vision_encoder",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 14,
    "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,
    "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,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "vocab_size": 152064
}