model_config.json

{
    "model_class": "FineTuneVisualGLMModel",
    "tokenizer_type": "THUDM/chatglm-6b",
    "num_layers": 28,
    "hidden_size": 4096,
    "num_attention_heads": 32,
    "vocab_size": 130528,
    "layernorm_order": "post",
    "model_parallel_size": 1,
    "max_sequence_length": 2048,
    "pre_seq_len": 128,
    "lora_rank": 10,
    "use_ptuning": false,
    "use_lora": true,
    "image_length": 32,
    "eva_args": {
        "num_layers": 39,
        "hidden_size": 1408,
        "num_attention_heads": 16,
        "vocab_size": 1,
        "layernorm_order": "pre",
        "model_parallel_size": 1,
        "max_sequence_length": 257,
        "inner_hidden_size": 6144,
        "use_final_layernorm": false,
        "layernorm_epsilon": 1e-06,
        "image_size": [
            224,
            224
        ],
        "pre_len": 1,
        "post_len": 0,
        "in_channels": 3,
        "num_classes": 0,
        "patch_size": 14
    },
    "qformer_args": {
        "num_layers": 12,
        "hidden_size": 768,
        "num_attention_heads": 12,
        "vocab_size": 32,
        "layernorm_order": "post",
        "model_parallel_size": 1,
        "max_sequence_length": 0,
        "is_decoder": [
            true,
            false,
            true,
            false,
            true,
            false,
            true,
            false,
            true,
            false,
            true,
            false
        ],
        "cross_attn_hidden_size": 1408,
        "layernorm_epsilon": 1e-12
    },
    "bos_token_id": 130004,
    "mask_token_id": 130000,
    "gmask_token_id": 130001,
    "image_size": [
        224,
        224
    ],
    "pre_len": 1,
    "post_len": 0,
    "in_channels": 3,
    "patch_size": 14
}