Team Ai
Modelpublic

Zythoz/gemma4-coding-agent

sourceHugging Faceupdated 6mo agoView on Hugging Face
1likes188downloads
config.json200 linesDownload Raw Back to root
1{2    "architectures": [3        "Gemma4ForConditionalGeneration"4    ],5    "audio_config": {6        "_name_or_path": "",7        "architectures": null,8        "attention_chunk_size": 12,9        "attention_context_left": 13,10        "attention_context_right": 0,11        "attention_invalid_logits_value": -1000000000.0,12        "attention_logit_cap": 50.0,13        "chunk_size_feed_forward": 0,14        "conv_kernel_size": 5,15        "torch_dtype": "bfloat16",16        "gradient_clipping": 10000000000.0,17        "hidden_act": "silu",18        "hidden_size": 1024,19        "id2label": {20            "0": "LABEL_0",21            "1": "LABEL_1"22        },23        "initializer_range": 0.02,24        "is_encoder_decoder": false,25        "label2id": {26            "LABEL_0": 0,27            "LABEL_1": 128        },29        "model_type": "gemma4_audio",30        "num_attention_heads": 8,31        "num_hidden_layers": 12,32        "output_attentions": false,33        "output_hidden_states": false,34        "output_proj_dims": 1536,35        "problem_type": null,36        "residual_weight": 0.5,37        "return_dict": true,38        "rms_norm_eps": 1e-06,39        "subsampling_conv_channels": [40            128,41            3242        ],43        "use_clipped_linears": true44    },45    "audio_token_id": 258881,46    "boa_token_id": 256000,47    "boi_token_id": 255999,48    "bos_token_id": 2,49    "torch_dtype": "bfloat16",50    "eoa_token_id": 258883,51    "eoa_token_index": 258883,52    "eoi_token_id": 258882,53    "eos_token_id": 106,54    "image_token_id": 258880,55    "initializer_range": 0.02,56    "model_name": "unsloth/gemma-4-E4B-it",57    "model_type": "gemma4",58    "pad_token_id": 0,59    "text_config": {60        "attention_bias": false,61        "attention_dropout": 0.0,62        "attention_k_eq_v": false,63        "bos_token_id": 2,64        "torch_dtype": "bfloat16",65        "enable_moe_block": false,66        "eos_token_id": 1,67        "expert_intermediate_size": null,68        "final_logit_softcapping": 30.0,69        "global_head_dim": 512,70        "head_dim": 256,71        "hidden_activation": "gelu_pytorch_tanh",72        "hidden_size": 2560,73        "hidden_size_per_layer_input": 256,74        "initializer_range": 0.02,75        "intermediate_size": 10240,76        "layer_types": [77            "sliding_attention",78            "sliding_attention",79            "sliding_attention",80            "sliding_attention",81            "sliding_attention",82            "full_attention",83            "sliding_attention",84            "sliding_attention",85            "sliding_attention",86            "sliding_attention",87            "sliding_attention",88            "full_attention",89            "sliding_attention",90            "sliding_attention",91            "sliding_attention",92            "sliding_attention",93            "sliding_attention",94            "full_attention",95            "sliding_attention",96            "sliding_attention",97            "sliding_attention",98            "sliding_attention",99            "sliding_attention",100            "full_attention",101            "sliding_attention",102            "sliding_attention",103            "sliding_attention",104            "sliding_attention",105            "sliding_attention",106            "full_attention",107            "sliding_attention",108            "sliding_attention",109            "sliding_attention",110            "sliding_attention",111            "sliding_attention",112            "full_attention",113            "sliding_attention",114            "sliding_attention",115            "sliding_attention",116            "sliding_attention",117            "sliding_attention",118            "full_attention"119        ],120        "max_position_embeddings": 131072,121        "model_type": "gemma4_text",122        "moe_intermediate_size": null,123        "num_attention_heads": 8,124        "num_experts": null,125        "num_global_key_value_heads": null,126        "num_hidden_layers": 42,127        "num_key_value_heads": 2,128        "num_kv_shared_layers": 18,129        "pad_token_id": 0,130        "rms_norm_eps": 1e-06,131        "rope_parameters": {132            "full_attention": {133                "partial_rotary_factor": 0.25,134                "rope_theta": 1000000.0,135                "rope_type": "proportional"136            },137            "sliding_attention": {138                "rope_theta": 10000.0,139                "rope_type": "default"140            }141        },142        "sliding_window": 512,143        "tie_word_embeddings": true,144        "top_k_experts": null,145        "use_bidirectional_attention": null,146        "use_cache": true,147        "use_double_wide_mlp": false,148        "vocab_size": 262144,149        "vocab_size_per_layer_input": 262144150    },151    "tie_word_embeddings": true,152    "unsloth_fixed": true,153    "unsloth_version": "2026.4.4",154    "use_cache": false,155    "video_token_id": 258884,156    "vision_config": {157        "_name_or_path": "",158        "architectures": null,159        "attention_bias": false,160        "attention_dropout": 0.0,161        "chunk_size_feed_forward": 0,162        "default_output_length": 280,163        "torch_dtype": "bfloat16",164        "global_head_dim": 64,165        "head_dim": 64,166        "hidden_activation": "gelu_pytorch_tanh",167        "hidden_size": 768,168        "id2label": {169            "0": "LABEL_0",170            "1": "LABEL_1"171        },172        "initializer_range": 0.02,173        "intermediate_size": 3072,174        "is_encoder_decoder": false,175        "label2id": {176            "LABEL_0": 0,177            "LABEL_1": 1178        },179        "max_position_embeddings": 131072,180        "model_type": "gemma4_vision",181        "num_attention_heads": 12,182        "num_hidden_layers": 16,183        "num_key_value_heads": 12,184        "output_attentions": false,185        "output_hidden_states": false,186        "patch_size": 16,187        "pooling_kernel_size": 3,188        "position_embedding_size": 10240,189        "problem_type": null,190        "return_dict": true,191        "rms_norm_eps": 1e-06,192        "rope_parameters": {193            "rope_theta": 100.0,194            "rope_type": "default"195        },196        "standardize": false,197        "use_clipped_linears": true198    },199    "vision_soft_tokens_per_image": 280200}