gemma4-vision-encoder / config.json
rnagabh's picture
Initial upload: Gemma 4 vision encoder (569.6M, 27-layer ViT with 2D RoPE)
93f12f3 verified
{
"_name_or_path": "",
"architectures": [
"Gemma4VisionModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"chunk_size_feed_forward": 0,
"default_output_length": 280,
"dtype": "bfloat16",
"global_head_dim": 72,
"head_dim": 72,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 1152,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 4304,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"max_position_embeddings": 131072,
"model_type": "gemma4_vision",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"num_key_value_heads": 16,
"output_attentions": false,
"output_hidden_states": false,
"patch_size": 16,
"pooling_kernel_size": 3,
"position_embedding_size": 10240,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 100.0,
"rope_type": "default"
},
"standardize": true,
"use_clipped_linears": false,
"torch_dtype": "bfloat16",
"_source_model": "google/gemma-4-31B-it",
"_extraction_note": "Vision tower extracted from 31B model",
"_verified_total_params": 569550384
}