prithivMLmods/Spatial-VU

1{2  "architectures": [3    "Qwen2_5_VLForConditionalGeneration"4  ],5  "attention_dropout": 0.0,6  "dtype": "bfloat16",7  "eos_token_id": 151645,8  "hidden_act": "silu",9  "hidden_size": 3584,10  "image_token_id": 151655,11  "initializer_range": 0.02,12  "intermediate_size": 18944,13  "max_position_embeddings": 128000,14  "max_window_layers": 28,15  "model_type": "qwen2_5_vl",16  "num_attention_heads": 28,17  "num_hidden_layers": 28,18  "num_key_value_heads": 4,19  "pad_token_id": 151643,20  "rms_norm_eps": 1e-06,21  "rope_scaling": {22    "mrope_section": [23      16,24      24,25      2426    ],27    "rope_type": "default",28    "type": "default"29  },30  "rope_theta": 1000000.0,31  "sliding_window": 32768,32  "text_config": {33    "_name_or_path": "inclusionAI/ViLaSR",34    "architectures": [35      "Qwen2_5_VLForConditionalGeneration"36    ],37    "attention_dropout": 0.0,38    "dtype": "bfloat16",39    "eos_token_id": 151645,40    "hidden_act": "silu",41    "hidden_size": 3584,42    "initializer_range": 0.02,43    "intermediate_size": 18944,44    "layer_types": [45      "full_attention",46      "full_attention",47      "full_attention",48      "full_attention",49      "full_attention",50      "full_attention",51      "full_attention",52      "full_attention",53      "full_attention",54      "full_attention",55      "full_attention",56      "full_attention",57      "full_attention",58      "full_attention",59      "full_attention",60      "full_attention",61      "full_attention",62      "full_attention",63      "full_attention",64      "full_attention",65      "full_attention",66      "full_attention",67      "full_attention",68      "full_attention",69      "full_attention",70      "full_attention",71      "full_attention",72      "full_attention"73    ],74    "max_position_embeddings": 128000,75    "max_window_layers": 28,76    "model_type": "qwen2_5_vl_text",77    "num_attention_heads": 28,78    "num_hidden_layers": 28,79    "num_key_value_heads": 4,80    "pad_token_id": 151643,81    "rms_norm_eps": 1e-06,82    "rope_scaling": {83      "mrope_section": [84        16,85        24,86        2487      ],88      "rope_type": "default",89      "type": "default"90    },91    "rope_theta": 1000000.0,92    "sliding_window": null,93    "use_cache": true,94    "use_sliding_window": false,95    "vision_token_id": 151654,96    "vocab_size": 15206497  },98  "tie_word_embeddings": false,99  "transformers_version": "4.57.1",100  "use_cache": true,101  "use_sliding_window": false,102  "video_token_id": 151656,103  "vision_config": {104    "depth": 32,105    "dtype": "bfloat16",106    "fullatt_block_indexes": [107      7,108      15,109      23,110      31111    ],112    "hidden_act": "silu",113    "hidden_size": 1280,114    "in_channels": 3,115    "in_chans": 3,116    "initializer_range": 0.02,117    "intermediate_size": 3420,118    "model_type": "qwen2_5_vl",119    "num_heads": 16,120    "out_hidden_size": 3584,121    "patch_size": 14,122    "spatial_merge_size": 2,123    "spatial_patch_size": 14,124    "temporal_patch_size": 2,125    "tokens_per_second": 2,126    "window_size": 112127  },128  "vision_end_token_id": 151653,129  "vision_start_token_id": 151652,130  "vision_token_id": 151654,131  "vocab_size": 152064132}133