|
{ |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"Gemma3nForConditionalGeneration" |
|
], |
|
"audio_config": { |
|
"return_dict": true, |
|
"output_hidden_states": false, |
|
"torchscript": false, |
|
"torch_dtype": "bfloat16", |
|
"use_bfloat16": false, |
|
"tf_legacy_loss": false, |
|
"pruned_heads": {}, |
|
"tie_word_embeddings": true, |
|
"chunk_size_feed_forward": 0, |
|
"is_encoder_decoder": false, |
|
"is_decoder": false, |
|
"cross_attention_hidden_size": null, |
|
"add_cross_attention": false, |
|
"tie_encoder_decoder": false, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"num_beams": 1, |
|
"num_beam_groups": 1, |
|
"diversity_penalty": 0.0, |
|
"temperature": 1.0, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"typical_p": 1.0, |
|
"repetition_penalty": 1.0, |
|
"length_penalty": 1.0, |
|
"no_repeat_ngram_size": 0, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"bad_words_ids": null, |
|
"num_return_sequences": 1, |
|
"output_scores": false, |
|
"return_dict_in_generate": false, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"remove_invalid_values": false, |
|
"exponential_decay_length_penalty": null, |
|
"suppress_tokens": null, |
|
"begin_suppress_tokens": null, |
|
"architectures": null, |
|
"finetuning_task": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"tokenizer_class": null, |
|
"prefix": null, |
|
"bos_token_id": null, |
|
"pad_token_id": null, |
|
"eos_token_id": null, |
|
"sep_token_id": null, |
|
"decoder_start_token_id": null, |
|
"task_specific_params": null, |
|
"problem_type": null, |
|
"_name_or_path": "", |
|
"conf_positional_bias_size": 256, |
|
"model_type": "gemma3n_audio", |
|
"sscp_conv_eps": 0.001, |
|
"input_feat_size": 128, |
|
"hidden_size": 1536, |
|
"rms_norm_eps": 1e-06, |
|
"vocab_size": 128, |
|
"vocab_offset": 262272, |
|
"gradient_clipping": 10000000000.0, |
|
"conf_attention_chunk_size": 12, |
|
"conf_attention_context_left": 13, |
|
"conf_attention_context_right": 0, |
|
"conf_attention_logit_cap": 50.0, |
|
"conf_num_attention_heads": 8, |
|
"conf_num_hidden_layers": 12, |
|
"conf_conv_kernel_size": 5, |
|
"conf_reduction_factor": 4, |
|
"conf_residual_weight": 0.5, |
|
"sscp_conv_channel_size": [ |
|
128, |
|
32 |
|
], |
|
"sscp_conv_group_norm_eps": 0.001, |
|
"sscp_conv_kernel_size": [ |
|
[ |
|
3, |
|
3 |
|
], |
|
[ |
|
3, |
|
3 |
|
] |
|
], |
|
"sscp_conv_stride_size": [ |
|
[ |
|
2, |
|
2 |
|
], |
|
[ |
|
2, |
|
2 |
|
] |
|
], |
|
"output_attentions": false |
|
}, |
|
"audio_soft_tokens_per_image": 188, |
|
"audio_token_id": 262273, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"boa_token_id": 256000, |
|
"boi_token_id": 255999, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eoa_token_id": 262272, |
|
"eoi_token_id": 262144, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"image_token_id": 262145, |
|
"initializer_range": 0.02, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "gemma3n", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"text_config": { |
|
"return_dict": true, |
|
"output_hidden_states": false, |
|
"torchscript": false, |
|
"torch_dtype": "bfloat16", |
|
"use_bfloat16": false, |
|
"tf_legacy_loss": false, |
|
"pruned_heads": {}, |
|
"tie_word_embeddings": true, |
|
"chunk_size_feed_forward": 0, |
|
"is_encoder_decoder": false, |
|
"is_decoder": false, |
|
"cross_attention_hidden_size": null, |
|
"add_cross_attention": false, |
|
"tie_encoder_decoder": false, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"num_beams": 1, |
|
"num_beam_groups": 1, |
|
"diversity_penalty": 0.0, |
|
"temperature": 1.0, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"typical_p": 1.0, |
|
"repetition_penalty": 1.0, |
|
"length_penalty": 1.0, |
|
"no_repeat_ngram_size": 0, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"bad_words_ids": null, |
|
"num_return_sequences": 1, |
|
"output_scores": false, |
|
"return_dict_in_generate": false, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"remove_invalid_values": false, |
|
"exponential_decay_length_penalty": null, |
|
"suppress_tokens": null, |
|
"begin_suppress_tokens": null, |
|
"architectures": null, |
|
"finetuning_task": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"tokenizer_class": null, |
|
"prefix": null, |
|
"bos_token_id": 2, |
|
"pad_token_id": 0, |
|
"eos_token_id": 1, |
|
"sep_token_id": null, |
|
"decoder_start_token_id": null, |
|
"task_specific_params": null, |
|
"problem_type": null, |
|
"_name_or_path": "", |
|
"altup_lr_multiplier": 1.0, |
|
"model_type": "gemma3n_text", |
|
"query_pre_attn_scalar": 256, |
|
"vocab_size": 262400, |
|
"vocab_size_per_layer_input": 262144, |
|
"max_position_embeddings": 32768, |
|
"hidden_size": 2048, |
|
"intermediate_size": [ |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384, |
|
16384 |
|
], |
|
"num_hidden_layers": 35, |
|
"num_attention_heads": 8, |
|
"head_dim": 256, |
|
"num_key_value_heads": 2, |
|
"initializer_range": 0.02, |
|
"rms_norm_eps": 1e-06, |
|
"use_cache": true, |
|
"rope_theta": 1000000.0, |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"hidden_activation": "gelu_pytorch_tanh", |
|
"sliding_window": 512, |
|
"final_logit_softcapping": 30.0, |
|
"layer_types": [ |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"full_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"full_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"full_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"full_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"full_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"full_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"sliding_attention", |
|
"full_attention" |
|
], |
|
"rope_local_base_freq": 10000.0, |
|
"rope_scaling": null, |
|
"hidden_size_per_layer_input": 256, |
|
"num_kv_shared_layers": 15, |
|
"altup_active_idx": 0, |
|
"altup_coef_clip": 120.0, |
|
"altup_correct_scale": true, |
|
"altup_num_inputs": 4, |
|
"laurel_rank": 64, |
|
"activation_sparsity_pattern": [ |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.95, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0, |
|
0.0 |
|
], |
|
"output_attentions": false |
|
}, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torchscript": false, |
|
"transformers_version": "4.53.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"vision_config": { |
|
"return_dict": true, |
|
"output_hidden_states": false, |
|
"torchscript": false, |
|
"torch_dtype": "bfloat16", |
|
"use_bfloat16": false, |
|
"tf_legacy_loss": false, |
|
"pruned_heads": {}, |
|
"tie_word_embeddings": true, |
|
"chunk_size_feed_forward": 0, |
|
"is_encoder_decoder": false, |
|
"is_decoder": false, |
|
"cross_attention_hidden_size": null, |
|
"add_cross_attention": false, |
|
"tie_encoder_decoder": false, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"num_beams": 1, |
|
"num_beam_groups": 1, |
|
"diversity_penalty": 0.0, |
|
"temperature": 1.0, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"typical_p": 1.0, |
|
"repetition_penalty": 1.0, |
|
"length_penalty": 1.0, |
|
"no_repeat_ngram_size": 0, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"bad_words_ids": null, |
|
"num_return_sequences": 1, |
|
"output_scores": false, |
|
"return_dict_in_generate": false, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"remove_invalid_values": false, |
|
"exponential_decay_length_penalty": null, |
|
"suppress_tokens": null, |
|
"begin_suppress_tokens": null, |
|
"architectures": null, |
|
"finetuning_task": null, |
|
"tokenizer_class": null, |
|
"prefix": null, |
|
"bos_token_id": null, |
|
"pad_token_id": null, |
|
"eos_token_id": null, |
|
"sep_token_id": null, |
|
"decoder_start_token_id": null, |
|
"task_specific_params": null, |
|
"problem_type": null, |
|
"_name_or_path": "", |
|
"label_names": [ |
|
"LABEL_0", |
|
"LABEL_1" |
|
], |
|
"model_type": "gemma3n_vision", |
|
"num_classes": 2, |
|
"initializer_range": 0.02, |
|
"do_pooling": true, |
|
"architecture": "mobilenetv5_300m_enc", |
|
"hidden_size": 2048, |
|
"vocab_size": 128, |
|
"vocab_offset": 262144, |
|
"rms_norm_eps": 1e-06, |
|
"output_attentions": false |
|
}, |
|
"vision_soft_tokens_per_image": 256 |
|
} |