| { |
| "architectures": [ |
| "Gemma3ForConditionalGeneration" |
| ], |
| "boi_token_index": 255999, |
| "eoi_token_index": 256000, |
| "eos_token_id": [ |
| 1, |
| 106 |
| ], |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2", |
| "3": "LABEL_3", |
| "4": "LABEL_4", |
| "5": "LABEL_5", |
| "6": "LABEL_6", |
| "7": "LABEL_7", |
| "8": "LABEL_8", |
| "9": "LABEL_9", |
| "10": "LABEL_10", |
| "11": "LABEL_11", |
| "12": "LABEL_12", |
| "13": "LABEL_13", |
| "14": "LABEL_14", |
| "15": "LABEL_15", |
| "16": "LABEL_16" |
| }, |
| "image_token_index": 262144, |
| "initializer_range": 0.02, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_10": 10, |
| "LABEL_11": 11, |
| "LABEL_12": 12, |
| "LABEL_13": 13, |
| "LABEL_14": 14, |
| "LABEL_15": 15, |
| "LABEL_16": 16, |
| "LABEL_2": 2, |
| "LABEL_3": 3, |
| "LABEL_4": 4, |
| "LABEL_5": 5, |
| "LABEL_6": 6, |
| "LABEL_7": 7, |
| "LABEL_8": 8, |
| "LABEL_9": 9 |
| }, |
| "mm_tokens_per_image": 256, |
| "model_type": "gemma3", |
| "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, |
| "use_cache": true, |
| "vocab_size": 262208 |
| }, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.50.0", |
| "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, |
| "vision_use_head": false |
| } |
| } |
|
|
