{
  "_name_or_path": "THUDM/visualglm-6b",
  "architectures": [
    "ChatGLMModel"
  ],
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "visualglm",
  "num_query_tokens": 32,
  "dtype": "float16",
  "vision_config": {
        "hidden_size": 1408,
        "intermediate_size": 6144,
        "num_hidden_layers": 39, 
        "num_attention_heads": 16,
        "num_channels": 3, 
        "image_size": 224,
        "patch_size": 14,
        "hidden_act": "gelu",
        "layer_norm_eps": 1e-06,
        "dropout": 0.1,
        "attention_dropout": 0.1,
        "initializer_range": 1e-10,
        "initializer_factor": 1.0,
        "model_type": "visualglm_vision_model",
        "vocab_size": 1,
        "layernorm_order": "pre",
        "model_parallel_size": 1,
        "max_sequence_length": 257,
        "use_final_layernorm": false,
        "pre_len": 1,
        "post_len": 0, 
        "num_classes": 0
    },
    "qformer_config": {
        "hidden_size": 768,
        "num_hidden_layers": 12,
        "num_attention_heads": 12,
        "intermediate_size": 3072,
        "hidden_act": "gelu",
        "hidden_dropout_prob": 0.1,
        "attention_probs_dropout_prob": 0.1,
        "max_position_embeddings": 512,
        "initializer_range": 0.02,
        "layer_norm_eps": 1e-12,
        "pad_token_id": 0,
        "position_embedding_type": "absolute",
        "cross_attention_frequency": 2,
        "encoder_hidden_size": 1408,
        "model_type": "visualglm_qformer_model",
        "vocab_size": 32,
        "layernorm_order": "post",
        "model_parallel_size": 1,
        "max_sequence_length": 0
    },
    "text_config":{
        "bos_token_id": 130004,
        "eos_token_id": 130005,
        "mask_token_id": 130000,
        "gmask_token_id": 130001,
        "pad_token_id": 3,
        "hidden_size": 4096,
        "inner_hidden_size": 16384,
        "layernorm_epsilon": 1e-05,
        "max_sequence_length": 2048,
        "model_type": "chatglm",
        "num_attention_heads": 32,
        "num_layers": 28,
        "position_encoding_2d": true,
        "dtype": "float16",
        "use_cache": true,
        "vocab_size": 130528,
        "image_length": 32
    }

}
