OpenGVLab/ZeroGUI-AndroidLab-7B

1{2  "architectures": [3    "Qwen2VLForConditionalGeneration"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151643,7  "eos_token_id": 151645,8  "vision_start_token_id": 151652,9  "vision_end_token_id": 151653,10  "vision_token_id": 151654,11  "image_token_id": 151655,12  "video_token_id": 151656,13  "hidden_act": "silu",14  "hidden_size": 3584,15  "initializer_range": 0.02,16  "intermediate_size": 18944,17  "max_position_embeddings": 32768,18  "max_window_layers": 28,19  "model_type": "qwen2_vl",20  "num_attention_heads": 28,21  "num_hidden_layers": 28,22  "num_key_value_heads": 4,23  "rms_norm_eps": 1e-06,24  "rope_scaling": {25    "mrope_section": [26      16,27      24,28      2429    ],30    "rope_type": "default",31    "type": "default"32  },33  "rope_theta": 1000000.0,34  "sliding_window": 32768,35  "tie_word_embeddings": false,36  "torch_dtype": "bfloat16",37  "transformers_version": "4.47.0",38  "use_cache": false,39  "use_sliding_window": false,40  "vision_config": {41    "depth": 32,42    "embed_dim": 1280,43    "mlp_ratio": 4,44    "num_heads": 16,45    "in_chans": 3,46    "model_type": "qwen2_vl",47    "hidden_size": 3584,48    "patch_size": 14,49    "spatial_merge_size": 2,50    "spatial_patch_size": 14,51    "temporal_patch_size": 252  },53  "vocab_size": 15206454}