config.json

{
  "_name_or_path": "/data//models/Qwen/Qwen2.5-14B-Instruct/",
  "architectures": [
    "LongVITAForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_long_vita.LongVITAConfig",
    "AutoModelForCausalLM": "modeling_long_vita.LongVITAForCausalLM"
  },
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 13824,
  "max_position_embeddings": 1310720,
  "max_window_layers": 70,
  "model_type": "long_vita",
  "num_attention_heads": 40,
  "num_hidden_layers": 48,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.3",
  "use_cache": true,
  "use_sliding_window": false,
  "visual": {
    "architectures": [
      "InternVisionModel"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
      "AutoModel": "modeling_intern_vit.InternVisionModel"
    },
    "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",
    "transformers_version": "4.37.2",
    "use_flash_attn": true
  },
  "vocab_size": 152064
}