| { | |
| "architectures": [ | |
| "Gemma3MMForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "activation": "swish", | |
| "activation_checkpointing": { | |
| "interval": 1, | |
| "module": "transformer", | |
| "offload": false | |
| }, | |
| "attention_dim": 1024, | |
| "attention_heads": 16, | |
| "batch_norm": false, | |
| "bias_in_glu": true, | |
| "causal": true, | |
| "chunk_size": -1, | |
| "cnn_layer_norm": true, | |
| "conv_activation": "swish", | |
| "conv_glu_type": "swish", | |
| "depthwise_multiplier": 1, | |
| "depthwise_seperable_out_channel": 1024, | |
| "dropout_rate": 0.0, | |
| "encoder_embedding_config": { | |
| "input_size": 80 | |
| }, | |
| "ext_pw_kernel_size": 1, | |
| "ext_pw_out_channel": 1024, | |
| "input_layer": "nemo_conv", | |
| "input_size": 80, | |
| "kernel_size": 3, | |
| "left_chunk": 18, | |
| "linear_units": 1536, | |
| "model_type": "gemma3_audio", | |
| "nemo_conv_settings": { | |
| "conv_channels": 1024 | |
| }, | |
| "num_blocks": 24, | |
| "relative_attention_bias_args": { | |
| "t5_bias_max_distance": 500, | |
| "type": "t5" | |
| }, | |
| "time_reduction": 8, | |
| "torch_dtype": "bfloat16" | |
| }, | |
| "audio_token_index": 262143, | |
| "auto_map": { | |
| "AutoConfig": "junnei/gemma-3-4b-it-speech--configuration_gemma3mm.Gemma3MMConfig", | |
| "AutoModel": "junnei/gemma-3-4b-it-speech--modeling_gemma3mm.Gemma3MMForConditionalGeneration" | |
| }, | |
| "boa_token_index": 256001, | |
| "boi_token_index": 255999, | |
| "eoa_token_index": 256002, | |
| "eoi_token_index": 256000, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "image_token_index": 262144, | |
| "initializer_range": 0.02, | |
| "mm_tokens_per_image": 256, | |
| "model_type": "gemma3mm", | |
| "speech_lora": { | |
| "dp": 0.01, | |
| "layer": "((layers.*self_attn\\.(q|k|v|o)_proj)|(layers.*mlp\\.(gate|up|down)_proj))", | |
| "lora_alpha": 320, | |
| "r": 320, | |
| "use_rslora": true | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "cache_implementation": "hybrid", | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 34, | |
| "num_key_value_heads": 4, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "rope_type": "linear" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 1024, | |
| "sliding_window_pattern": 6, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "vocab_size": 262208 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.0.dev0", | |
| "use_cache": false, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 896, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14, | |
| "torch_dtype": "bfloat16", | |
| "vision_use_head": false | |
| } | |
| } | |