{
    "_commit_hash": null,
    "architectures": [
        "YuanVLChatModel"
    ],
    "auto_map": {
        "AutoConfig": "configuration_yuanvl.YuanVLChatConfig",
        "AutoModel": "modeling_yuanvl_chat.YuanVLChatModel",
        "AutoModelForCausalLM": "modeling_yuanvl_chat.YuanVLChatModel"
    },
    "clip_download_path": "path/to/internvit-448",
    "clip_model_name": "InternViT-448",
    "imagemlp_recompute": true,
    "downsample_ratio": 0.5,
    "dynamic_image_size": true,
    "force_image_size": 448,
    "max_dynamic_patch": 9,
    "min_dynamic_patch": 1,
    "model_type": "yuanvl",
    "ps_version": "v2",
    "select_layer": -1,
    "template": "yuan-chat",
    "torch_dtype": "bfloat16",
    "use_backbone_lora": 0,
    "use_llm_lora": 0,
    "use_thumbnail": true,
    "img_context_token_id": 77188,
    "attention_dropout": 0.0,
    "vision_config": {
        "architectures": [
            "InternVisionModel"
        ],
        "attention_dropout": 0.0,
        "drop_path_rate": 0.0,
        "dropout": 0.0,
        "hidden_act": "gelu",
        "hidden_size": 1024,
        "image_size": 448,
        "initializer_factor": 1.0,
        "initializer_range": 0.02,
        "intermediate_size": 4096,
        "layer_norm_eps": 1e-06,
        "model_type": "intern_vit_6b",
        "norm_type": "layer_norm",
        "num_attention_heads": 16,
        "num_channels": 3,
        "num_hidden_layers": 24,
        "output_attentions": false,
        "output_hidden_states": false,
        "patch_size": 14,
        "qk_normalization": false,
        "qkv_bias": true,
        "return_dict": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.2",
        "use_bfloat16": true,
        "use_flash_attn": true
    },
    "llm_config": {
        "_from_model_config": true,
        "architectures": [
            "YuanForCausalLM"
        ],
        "attention_projection_size": 4096,
        "attn_dropout": 0.0,
        "auto_map": {
            "AutoConfig": "configuration_yuanvl.YuanConfig",
            "AutoModelForCausalLM": "yuanvl.YuanForCausalLM"
        },
        "causal_mask": true,
        "attn_mask_type": "causal",
        "dropout": 0,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "use_lf_gate": true,
        "lf_conv2d_group": 1,
        "lf_conv2d_num_pad": 0,
        "use_lfa_bias": true,
        "mask_token_id": 77185,
        "max_position_embeddings": 131072,
        "model_max_length": 131072,
        "model_type": "yuan",
        "ffn_hidden_size": 8192,
        "moe_config": {
            "moe_num_experts": 32,
            "moe_top_k": 2,
            "norm_topk_prob": true,
            "num_attention_router_heads": 1,
            "gated_linear_unit": true,
            "ffn_hidden_size": 8192,
            "router_type": "attn_router"
        },
        "num_attention_heads": 16,
        "num_hidden_layers": 24,
        "output_router_logits": true,
        "pad_token_id": 77188,
        "reset_attention_mask": false,
        "reset_position_ids": false,
        "rms_norm_eps": 1e-06,
        "rotary_base": 1000000,
        "rotary_percent": 0.5,
        "tie_word_embeddings": false,
        "rep_token": "<rep>",
        "rep_token_id": 134962,
        "eod_token": "<eod>",
        "eod_token_id": 77185,
        "bos_token": "<BOS>",
        "bos_token_id": 134960,
        "sep_token": "<sep>",
        "sep_token_id": 77187,
        "tokenizer_class": "YuanVLTokenizer",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.2",
        "use_cache": true,
        "use_flash_attention": true,
        "use_loss_mask": false,
        "use_moe": true,
        "vocab_size": 136064,
        "use_bias": false,
        "use_rope_scaling": false,
        "head_dim": 256
    },
    "eos_token_id": 77185
}