CoolFace
Modelpublic

Titaniumclock/Gemma-4-Rust-Coder

sourceHugging Facemitupdated 4mo agoView on Hugging Face
0likes165downloads
config.json191 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    "torch_dtype": "bfloat16",49    "eoa_token_id": 258883,50    "eoa_token_index": 258883,51    "eoi_token_id": 258882,52    "eos_token_id": 1,53    "image_token_id": 258880,54    "initializer_range": 0.02,55    "model_name": "unsloth/gemma-4-e2b-it-unsloth-bnb-4bit",56    "model_type": "gemma4",57    "pad_token_id": 0,58    "text_config": {59        "attention_bias": false,60        "attention_dropout": 0.0,61        "attention_k_eq_v": false,62        "bos_token_id": 2,63        "torch_dtype": "bfloat16",64        "enable_moe_block": false,65        "eos_token_id": 1,66        "expert_intermediate_size": null,67        "final_logit_softcapping": 30.0,68        "global_head_dim": 512,69        "head_dim": 256,70        "hidden_activation": "gelu_pytorch_tanh",71        "hidden_size": 1536,72        "hidden_size_per_layer_input": 256,73        "initializer_range": 0.02,74        "intermediate_size": 6144,75        "layer_types": [76            "sliding_attention",77            "sliding_attention",78            "sliding_attention",79            "sliding_attention",80            "full_attention",81            "sliding_attention",82            "sliding_attention",83            "sliding_attention",84            "sliding_attention",85            "full_attention",86            "sliding_attention",87            "sliding_attention",88            "sliding_attention",89            "sliding_attention",90            "full_attention",91            "sliding_attention",92            "sliding_attention",93            "sliding_attention",94            "sliding_attention",95            "full_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            "full_attention",106            "sliding_attention",107            "sliding_attention",108            "sliding_attention",109            "sliding_attention",110            "full_attention"111        ],112        "max_position_embeddings": 131072,113        "model_type": "gemma4_text",114        "moe_intermediate_size": null,115        "num_attention_heads": 8,116        "num_experts": null,117        "num_global_key_value_heads": null,118        "num_hidden_layers": 35,119        "num_key_value_heads": 1,120        "num_kv_shared_layers": 20,121        "pad_token_id": 0,122        "rms_norm_eps": 1e-06,123        "rope_parameters": {124            "full_attention": {125                "partial_rotary_factor": 0.25,126                "rope_theta": 1000000.0,127                "rope_type": "proportional"128            },129            "sliding_attention": {130                "rope_theta": 10000.0,131                "rope_type": "default"132            }133        },134        "sliding_window": 512,135        "tie_word_embeddings": true,136        "top_k_experts": null,137        "use_bidirectional_attention": null,138        "use_cache": true,139        "use_double_wide_mlp": true,140        "vocab_size": 262144,141        "vocab_size_per_layer_input": 262144142    },143    "tie_word_embeddings": true,144    "unsloth_fixed": true,145    "unsloth_version": "2026.4.5",146    "video_token_id": 258884,147    "vision_config": {148        "_name_or_path": "",149        "architectures": null,150        "attention_bias": false,151        "attention_dropout": 0.0,152        "chunk_size_feed_forward": 0,153        "default_output_length": 280,154        "torch_dtype": "bfloat16",155        "global_head_dim": 64,156        "head_dim": 64,157        "hidden_activation": "gelu_pytorch_tanh",158        "hidden_size": 768,159        "id2label": {160            "0": "LABEL_0",161            "1": "LABEL_1"162        },163        "initializer_range": 0.02,164        "intermediate_size": 3072,165        "is_encoder_decoder": false,166        "label2id": {167            "LABEL_0": 0,168            "LABEL_1": 1169        },170        "max_position_embeddings": 131072,171        "model_type": "gemma4_vision",172        "num_attention_heads": 12,173        "num_hidden_layers": 16,174        "num_key_value_heads": 12,175        "output_attentions": false,176        "output_hidden_states": false,177        "patch_size": 16,178        "pooling_kernel_size": 3,179        "position_embedding_size": 10240,180        "problem_type": null,181        "return_dict": true,182        "rms_norm_eps": 1e-06,183        "rope_parameters": {184            "rope_theta": 100.0,185            "rope_type": "default"186        },187        "standardize": false,188        "use_clipped_linears": true189    },190    "vision_soft_tokens_per_image": 280191}