config.json

{
  "architectures": [
    "YuanVLChatModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_yuanvl.YuanVLChatConfig",
    "AutoModel": "modeling_yuanvl_chat.YuanVLChatModel",
    "AutoModelForCausalLM": "modeling_yuanvl_chat.YuanVLChatModel"
  },
  "bos_token_id": 134960,
  "clip_download_path": "internvit2.5-300M",
  "clip_model_name": "InternViT-448",
  "downsample_ratio": 0.5,
  "dynamic_image_size": true,
  "eos_token_id": 77185,
  "force_image_size": 448,
  "imagemlp_recompute": true,
  "img_context_token_id": 77188,
  "llm_config": {
    "_from_model_config": true,
    "architectures": [
      "YuanForCausalLM"
    ],
    "attention_dropout": 0.0,
    "attention_projection_size": 9216,
    "attn_dropout": 0.0,
    "attn_mask_type": "causal",
    "auto_map": {
      "AutoConfig": "configuration_yuanvl.YuanConfig",
      "AutoModelForCausalLM": "yuanvl.YuanForCausalLM"
    },
    "bos_token": "<BOS>",
    "bos_token_id": 134960,
    "causal_mask": true,
    "dropout": 0,
    "eod_token": "<eod>",
    "eod_token_id": 77185,
    "ffn_hidden_size": 16384,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 4608,
    "initializer_range": 0.02,
    "intermediate_size": 16384,
    "lf_conv2d_add_bias": false,
    "lf_conv2d_group": 1,
    "lf_conv2d_num_pad": 0,
    "mask_token_id": 77185,
    "max_position_embeddings": 32768,
    "model_max_length": 32768,
    "model_type": "yuan",
    "moe_config": {
      "ffn_hidden_size": 16384,
      "gated_linear_unit": true,
      "moe_num_experts": 64,
      "moe_top_k": 2,
      "norm_topk_prob": true,
      "per_layer_experts_blocks": [
        40,
        48,
        24,
        16,
        24,
        16,
        16,
        24,
        32,
        32,
        24,
        24,
        24,
        40,
        40,
        40,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        48,
        40,
        40,
        40,
        40,
        40,
        40,
        40,
        40,
        32,
        32,
        32,
        32,
        32,
        32,
        24,
        24,
        16,
        8
      ],
      "router_type": "linear"
    },
    "num_attention_heads": 36,
    "num_hidden_layers": 103,
    "num_key_value_heads": 36,
    "num_query_groups": 36,
    "output_router_logits": false,
    "pad_token_id": 77188,
    "perform_initialization": false,
    "reset_attention_mask": false,
    "reset_position_ids": false,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "rotary_base": 1000000,
    "rotary_percent": 1.0,
    "sep_token": "<sep>",
    "sep_token_id": 77187,
    "tie_word_embeddings": false,
    "tokenizer_class": "YuanVLTokenizer",
    "torch_dtype": "bfloat16",
    "use_bias": false,
    "use_cache": true,
    "use_flash_attention": true,
    "use_lf_gate": true,
    "use_lfa_bias": false,
    "use_loss_mask": false,
    "use_moe": true,
    "use_rope_scaling": false,
    "vocab_size": 136064
  },
  "max_dynamic_patch": 9,
  "max_position_embeddings": 32768,
  "min_dynamic_patch": 1,
  "model_max_length": 32768,
  "model_type": "yuanvl",
  "output_attentions": false,
  "pad_token_id": 77185,
  "ps_version": "v2",
  "select_layer": -1,
  "template": "yuan-chat",
  "torch_dtype": "bfloat16",
  "transformers_version": null,
  "use_backbone_lora": 0,
  "use_llm_lora": 0,
  "use_thumbnail": true,
  "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,
    "patch_size": 14,
    "qk_normalization": false,
    "qkv_bias": true,
    "torch_dtype": "bfloat16",
    "use_bfloat16": true,
    "use_flash_attn": true
  }
}