gemma3n-text-matformer / config.json
varshu23's picture
Upload folder using huggingface_hub
0593473 verified
{
"architectures": [
"Gemma3nForConditionalGeneration"
],
"audio_soft_tokens_per_image": 188,
"audio_token_id": 262273,
"boa_token_id": 256000,
"boi_token_id": 255999,
"dtype": "bfloat16",
"eoa_token_id": 262272,
"eoi_token_id": 262144,
"eos_token_id": [
1,
106
],
"image_token_id": 262145,
"initializer_range": 0.02,
"model_type": "gemma3n",
"text_config": {
"activation_sparsity_pattern": [
0.95,
0.95,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"altup_active_idx": 0,
"altup_coef_clip": 120.0,
"altup_correct_scale": true,
"altup_num_inputs": 4,
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"final_logit_softcapping": 30.0,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2048,
"hidden_size_per_layer_input": 256,
"initializer_range": 0.02,
"intermediate_size": [
2048,
2048,
2048,
2048,
2048,
2048,
2048,
2048,
2048,
2048,
2048,
2048
],
"laurel_rank": 64,
"layer_types": [
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"model_type": "gemma3n_text",
"num_attention_heads": 8,
"num_hidden_layers": 12,
"num_key_value_heads": 2,
"num_kv_shared_layers": 10,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000.0,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 512,
"use_cache": true,
"vocab_size": 262400,
"vocab_size_per_layer_input": 262144
},
"transformers_version": "4.57.3",
"vision_soft_tokens_per_image": 256
}