config.json

{
  "architectures": [
    "JinaEmbeddingsV5OmniModel"
  ],
  "auto_map": {
    "AutoConfig": "modeling_jina_embeddings_v5_omni.JinaEmbeddingsV5OmniConfig",
    "AutoModel": "modeling_jina_embeddings_v5_omni.JinaEmbeddingsV5OmniModel"
  },
  "model_type": "jina_embeddings_v5_omni",
  "task_names": [
    "retrieval",
    "text-matching",
    "clustering",
    "classification"
  ],
  "special_token_ids": [
    128256,
    128257,
    128258,
    128259
  ],
  "vision_config": {
    "deepstack_visual_indexes": [],
    "depth": 12,
    "dtype": "bfloat16",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "model_type": "",
    "num_heads": 12,
    "num_position_embeddings": 2304,
    "out_hidden_size": 1024,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_causal": false,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "model_type": "",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "num_key_value_heads": 12,
    "pad_token_id": null,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "rope_theta": 1000000.0,
      "rope_type": "default"
    },
    "tie_word_embeddings": false,
    "vocab_size": 128260
  },
  "audio_config": {
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "attention_dropout": 0.0,
    "d_model": 1280,
    "dropout": 0.0,
    "dtype": "float32",
    "encoder_attention_heads": 20,
    "encoder_ffn_dim": 5120,
    "encoder_layers": 32,
    "initializer_range": 0.02,
    "max_source_positions": 1500,
    "num_mel_bins": 128,
    "scale_embedding": false,
    "n_window": 100,
    "output_dim": 3584
  },
  "image_token_index": 128259,
  "audio_token_id": 128256,
  "audio_start_token_id": 128257,
  "audio_end_token_id": 128258,
  "projector_hidden_act": "gelu",
  "tie_word_embeddings": false,
  "dtype": "bfloat16",
  "transformers_version": "5.4.0",
  "torch_dtype": "bfloat16",
  "is_matryoshka": true,
  "matryoshka_dimensions": [
    32,
    64,
    128,
    256,
    512,
    768
  ]
}