config.json

{
  "_sliding_window_pattern": 6,
  "architectures": [
    "Gemma3TextForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": null,
  "bos_token_id": 2,
  "dtype": "bfloat16",
  "eos_token_id": 1,
  "final_logit_softcapping": null,
  "head_dim": 256,
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7",
    "8": "LABEL_8",
    "9": "LABEL_9"
  },
  "initializer_range": 0.02,
  "intermediate_size": 1152,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7,
    "LABEL_8": 8,
    "LABEL_9": 9
  },
  "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"
  ],
  "max_position_embeddings": 2048,
  "model_type": "gemma3_text",
  "num_attention_heads": 3,
  "num_hidden_layers": 24,
  "num_key_value_heads": 1,
  "pad_token_id": 0,
  "problem_type": "single_label_classification",
  "query_pre_attn_scalar": 256,
  "rms_norm_eps": 1e-06,
  "rope_local_base_freq": 10000.0,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 129,
  "transformers_version": "4.57.1",
  "use_bidirectional_attention": true,
  "use_cache": true,
  "vocab_size": 262144
}