CoolFace
Modelpublic

TitleOS/HomeGem4Bn

sourceHugging Facempl-2.0updated 11mo agoView on Hugging Face
0likes13downloads
config.json224 linesDownload Raw Back to root
1{2    "architectures": [3        "Gemma3nForConditionalGeneration"4    ],5    "audio_config": {6        "conf_attention_chunk_size": 12,7        "conf_attention_context_left": 13,8        "conf_attention_context_right": 0,9        "conf_attention_logit_cap": 50.0,10        "conf_conv_kernel_size": 5,11        "conf_num_attention_heads": 8,12        "conf_num_hidden_layers": 12,13        "conf_reduction_factor": 4,14        "conf_residual_weight": 0.5,15        "torch_dtype": "bfloat16",16        "gradient_clipping": 10000000000.0,17        "hidden_size": 1536,18        "input_feat_size": 128,19        "model_type": "gemma3n_audio",20        "rms_norm_eps": 1e-06,21        "sscp_conv_channel_size": [22            128,23            3224        ],25        "sscp_conv_group_norm_eps": 0.001,26        "sscp_conv_kernel_size": [27            [28                3,29                330            ],31            [32                3,33                334            ]35        ],36        "sscp_conv_stride_size": [37            [38                2,39                240            ],41            [42                2,43                244            ]45        ],46        "vocab_offset": 262272,47        "vocab_size": 12848    },49    "audio_soft_tokens_per_image": 188,50    "audio_token_id": 262273,51    "boa_token_id": 256000,52    "boi_token_id": 255999,53    "bos_token_id": 2,54    "torch_dtype": "bfloat16",55    "eoa_token_id": 262272,56    "eoi_token_id": 262144,57    "eos_token_id": 106,58    "image_token_id": 262145,59    "initializer_range": 0.02,60    "model_type": "gemma3n",61    "pad_token_id": 0,62    "text_config": {63        "activation_sparsity_pattern": [64            0.95,65            0.95,66            0.95,67            0.95,68            0.95,69            0.95,70            0.95,71            0.95,72            0.95,73            0.95,74            0.0,75            0.0,76            0.0,77            0.0,78            0.0,79            0.0,80            0.0,81            0.0,82            0.0,83            0.0,84            0.0,85            0.0,86            0.0,87            0.0,88            0.0,89            0.0,90            0.0,91            0.0,92            0.0,93            0.0,94            0.0,95            0.0,96            0.0,97            0.0,98            0.099        ],100        "altup_active_idx": 0,101        "altup_coef_clip": 120.0,102        "altup_correct_scale": true,103        "altup_num_inputs": 4,104        "attention_bias": false,105        "attention_dropout": 0.0,106        "torch_dtype": "bfloat16",107        "final_logit_softcapping": 30.0,108        "head_dim": 256,109        "hidden_activation": "gelu_pytorch_tanh",110        "hidden_size": 2048,111        "hidden_size_per_layer_input": 256,112        "initializer_range": 0.02,113        "intermediate_size": [114            16384,115            16384,116            16384,117            16384,118            16384,119            16384,120            16384,121            16384,122            16384,123            16384,124            16384,125            16384,126            16384,127            16384,128            16384,129            16384,130            16384,131            16384,132            16384,133            16384,134            16384,135            16384,136            16384,137            16384,138            16384,139            16384,140            16384,141            16384,142            16384,143            16384,144            16384,145            16384,146            16384,147            16384,148            16384149        ],150        "laurel_rank": 64,151        "layer_types": [152            "sliding_attention",153            "sliding_attention",154            "sliding_attention",155            "sliding_attention",156            "full_attention",157            "sliding_attention",158            "sliding_attention",159            "sliding_attention",160            "sliding_attention",161            "full_attention",162            "sliding_attention",163            "sliding_attention",164            "sliding_attention",165            "sliding_attention",166            "full_attention",167            "sliding_attention",168            "sliding_attention",169            "sliding_attention",170            "sliding_attention",171            "full_attention",172            "sliding_attention",173            "sliding_attention",174            "sliding_attention",175            "sliding_attention",176            "full_attention",177            "sliding_attention",178            "sliding_attention",179            "sliding_attention",180            "sliding_attention",181            "full_attention",182            "sliding_attention",183            "sliding_attention",184            "sliding_attention",185            "sliding_attention",186            "full_attention"187        ],188        "max_position_embeddings": 32768,189        "model_type": "gemma3n_text",190        "num_attention_heads": 8,191        "num_hidden_layers": 35,192        "num_key_value_heads": 2,193        "num_kv_shared_layers": 15,194        "rms_norm_eps": 1e-06,195        "rope_local_base_freq": 10000.0,196        "rope_scaling": null,197        "rope_theta": 1000000.0,198        "sliding_window": 512,199        "use_cache": true,200        "vocab_size": 262400,201        "vocab_size_per_layer_input": 262144202    },203    "transformers_version": "4.56.2",204    "unsloth_fixed": true,205    "unsloth_version": "2025.10.12",206    "vision_config": {207        "architecture": "mobilenetv5_300m_enc",208        "do_pooling": false,209        "torch_dtype": "bfloat16",210        "hidden_size": 2048,211        "initializer_range": 0.02,212        "label_names": [213            "LABEL_0",214            "LABEL_1"215        ],216        "model_args": null,217        "model_type": "gemma3n_vision",218        "num_classes": 2,219        "rms_norm_eps": 1e-06,220        "vocab_offset": 262144,221        "vocab_size": 128222    },223    "vision_soft_tokens_per_image": 256224}