CoolFace
Modelpublic

astroanand/astro-code-switch-0.5_7.9B

sourceHugging Facegemmaupdated 28d agoView on Hugging Face
1likes118downloads
config.json226 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        "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    "do_sample": true,49    "dtype": "bfloat16",50    "eoa_token_id": 258883,51    "eoa_token_index": 258883,52    "eoi_token_id": 258882,53    "eos_token_id": [54        1,55        106,56        5057    ],58    "generation_config": {59        "bos_token_id": 2,60        "do_sample": true,61        "eos_token_id": [62            1,63            106,64            5065        ],66        "pad_token_id": 0,67        "temperature": 1.0,68        "top_k": 64,69        "top_p": 0.95,70        "transformers_version": "5.5.0.dev0"71    },72    "image_token_id": 258880,73    "initializer_range": 0.02,74    "model_type": "gemma4",75    "quantization": {76        "group_size": 64,77        "bits": 4,78        "mode": "affine"79    },80    "quantization_config": {81        "group_size": 64,82        "bits": 4,83        "mode": "affine"84    },85    "temperature": 1.0,86    "text_config": {87        "attention_bias": false,88        "attention_dropout": 0.0,89        "attention_k_eq_v": false,90        "bos_token_id": 2,91        "dtype": "bfloat16",92        "enable_moe_block": false,93        "eos_token_id": 1,94        "expert_intermediate_size": null,95        "final_logit_softcapping": 30.0,96        "global_head_dim": 512,97        "head_dim": 256,98        "hidden_activation": "gelu_pytorch_tanh",99        "hidden_size": 2560,100        "hidden_size_per_layer_input": 256,101        "initializer_range": 0.02,102        "intermediate_size": 10240,103        "layer_types": [104            "sliding_attention",105            "sliding_attention",106            "sliding_attention",107            "sliding_attention",108            "sliding_attention",109            "full_attention",110            "sliding_attention",111            "sliding_attention",112            "sliding_attention",113            "sliding_attention",114            "sliding_attention",115            "full_attention",116            "sliding_attention",117            "sliding_attention",118            "sliding_attention",119            "sliding_attention",120            "sliding_attention",121            "full_attention",122            "sliding_attention",123            "sliding_attention",124            "sliding_attention",125            "sliding_attention",126            "sliding_attention",127            "full_attention",128            "sliding_attention",129            "sliding_attention",130            "sliding_attention",131            "sliding_attention",132            "sliding_attention",133            "full_attention",134            "sliding_attention",135            "sliding_attention",136            "sliding_attention",137            "sliding_attention",138            "sliding_attention",139            "full_attention",140            "sliding_attention",141            "sliding_attention",142            "sliding_attention",143            "sliding_attention",144            "sliding_attention",145            "full_attention"146        ],147        "max_position_embeddings": 131072,148        "model_type": "gemma4_text",149        "num_attention_heads": 8,150        "num_experts": null,151        "num_global_key_value_heads": null,152        "num_hidden_layers": 42,153        "num_key_value_heads": 2,154        "num_kv_shared_layers": 18,155        "pad_token_id": 0,156        "rms_norm_eps": 1e-06,157        "rope_parameters": {158            "full_attention": {159                "partial_rotary_factor": 0.25,160                "rope_theta": 1000000.0,161                "rope_type": "proportional"162            },163            "sliding_attention": {164                "rope_theta": 10000.0,165                "rope_type": "default"166            }167        },168        "sliding_window": 512,169        "tie_word_embeddings": true,170        "top_k_experts": null,171        "use_bidirectional_attention": null,172        "use_cache": true,173        "use_double_wide_mlp": false,174        "vocab_size": 262144,175        "vocab_size_per_layer_input": 262144176    },177    "tie_word_embeddings": true,178    "top_k": 64,179    "top_p": 0.95,180    "transformers_version": "5.5.0.dev0",181    "video_token_id": 258884,182    "vision_config": {183        "_name_or_path": "",184        "architectures": null,185        "attention_bias": false,186        "attention_dropout": 0.0,187        "chunk_size_feed_forward": 0,188        "default_output_length": 280,189        "dtype": "bfloat16",190        "global_head_dim": 64,191        "head_dim": 64,192        "hidden_activation": "gelu_pytorch_tanh",193        "hidden_size": 768,194        "id2label": {195            "0": "LABEL_0",196            "1": "LABEL_1"197        },198        "initializer_range": 0.02,199        "intermediate_size": 3072,200        "is_encoder_decoder": false,201        "label2id": {202            "LABEL_0": 0,203            "LABEL_1": 1204        },205        "max_position_embeddings": 131072,206        "model_type": "gemma4_vision",207        "num_attention_heads": 12,208        "num_hidden_layers": 16,209        "num_key_value_heads": 12,210        "output_attentions": false,211        "output_hidden_states": false,212        "patch_size": 16,213        "pooling_kernel_size": 3,214        "position_embedding_size": 10240,215        "problem_type": null,216        "return_dict": true,217        "rms_norm_eps": 1e-06,218        "rope_parameters": {219            "rope_theta": 100.0,220            "rope_type": "default"221        },222        "standardize": false,223        "use_clipped_linears": true224    },225    "vision_soft_tokens_per_image": 280226}