config.json

{
  "architectures": [
    "VisionTextDualEncoderModel"
  ],
  "logit_scale_init_value": 2.6592,
  "model_type": "vision-text-dual-encoder",
  "projection_dim": 512,
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "eos_token_id": 0,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 576,
    "initializer_range": 0.041666666666666664,
    "intermediate_size": 1536,
    "is_llama_config": true,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 9,
    "num_hidden_layers": 30,
    "num_key_value_heads": 3,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_interleaved": false,
    "rope_scaling": null,
    "rope_theta": 100000,
    "tie_word_embeddings": true,
    "torch_dtype": "float32",
    "use_cache": true,
    "vocab_size": 49152
  },
  "torch_dtype": "float32",
  "transformers_version": "4.50.0",
  "vision_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "facebook/dinov2-with-registers-base",
    "apply_layernorm": true,
    "architectures": [
      "Dinov2WithRegistersModel"
    ],
    "attention_probs_dropout_prob": 0.0,
    "drop_path_rate": 0.0,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "image_size": 518,
    "initializer_range": 0.02,
    "interpolate_antialias": true,
    "interpolate_offset": 0.0,
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "mlp_ratio": 4,
    "model_type": "dinov2_with_registers",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "num_register_tokens": 4,
    "out_features": [
      "stage12"
    ],
    "out_indices": [
      12
    ],
    "patch_size": 14,
    "qkv_bias": true,
    "reshape_hidden_states": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12"
    ],
    "torch_dtype": "float32",
    "use_swiglu_ffn": false
  }
}