text_encoder/config.json

{
  "architectures": [
    "T5Gemma2Encoder"
  ],
  "attention_dropout": 0.0,
  "boi_token_index": 255999,
  "dropout_rate": 0.0,
  "dtype": "bfloat16",
  "eoi_token_index": 256000,
  "image_token_index": 256001,
  "initializer_range": 0.02,
  "mm_tokens_per_image": 256,
  "model_type": "t5gemma2_encoder",
  "text_config": {
    "_sliding_window_pattern": 6,
    "add_cross_attention": false,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_logit_softcapping": null,
    "bos_token_id": 2,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "dropout_rate": 0.0,
    "dtype": "bfloat16",
    "eos_token_id": 1,
    "final_logit_softcapping": null,
    "finetuning_task": null,
    "head_dim": 256,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 10240,
    "is_decoder": false,
    "layer_types": [
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention"
    ],
    "max_position_embeddings": 131072,
    "model_type": "t5gemma2_text",
    "num_attention_heads": 8,
    "num_hidden_layers": 34,
    "num_key_value_heads": 4,
    "pad_token_id": 0,
    "prefix": null,
    "query_pre_attn_scalar": 256,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "full_attention": {
        "factor": 8.0,
        "rope_theta": 1000000,
        "rope_type": "linear"
      },
      "sliding_attention": {
        "rope_theta": 10000,
        "rope_type": "default"
      }
    },
    "sep_token_id": null,
    "sliding_window": 1024,
    "task_specific_params": null,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "use_bidirectional_attention": false,
    "use_cache": true,
    "vocab_size": 262144
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.5.4",
  "vision_config": {
    "add_cross_attention": false,
    "attention_dropout": 0.0,
    "bos_token_id": null,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "dropout_rate": 0.0,
    "dtype": "bfloat16",
    "eos_token_id": null,
    "finetuning_task": null,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 896,
    "intermediate_size": 4304,
    "is_decoder": false,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "pad_token_id": null,
    "patch_size": 14,
    "prefix": null,
    "sep_token_id": null,
    "task_specific_params": null,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "vision_use_head": false,
    "vocab_size": 262144
  },
  "vocab_size": 262144
}