config.json

{
  "architectures": [
    "InternVLForConditionalGeneration"
  ],
  "downsample_ratio": 0.5,
  "image_seq_length": 256,
  "image_token_id": 92546,
  "model_type": "internvl",
  "projector_hidden_act": "gelu",
  "text_config": {
    "architectures": [
      "InternLM2ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "max_position_embeddings": 32768,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "num_key_value_heads": 8,
    "pad_token_id": 2,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 2.0,
      "rope_type": "dynamic",
      "type": "dynamic"
    },
    "rope_theta": 1000000,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 92553
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.0.dev0",
  "vision_config": {
    "architectures": [
      "InternVisionModel"
    ],
    "attention_bias": true,
    "attention_dropout": 0.0,
    "dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 1024,
    "image_size": [
      448,
      448
    ],
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-06,
    "layer_scale_init_value": 0.1,
    "model_type": "internvl_vision",
    "norm_type": "layer_norm",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": [
      14,
      14
    ],
    "projection_dropout": 0.0,
    "torch_dtype": "bfloat16",
    "use_absolute_position_embeddings": true,
    "use_mask_token": false,
    "use_mean_pooling": true,
    "use_qk_norm": false
  },
  "vision_feature_layer": -1,
  "vision_feature_select_strategy": "default"
}