| { | |
| "architectures": [ | |
| "Gemma3ForConditionalGeneration" | |
| ], | |
| "boi_token_index": 250, | |
| "dtype": "bfloat16", | |
| "eoi_token_index": 251, | |
| "image_token_index": 252, | |
| "initializer_range": 0.02, | |
| "mm_tokens_per_image": 1, | |
| "model_type": "gemma3", | |
| "text_config": { | |
| "_sliding_window_pattern": 6, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": null, | |
| "head_dim": 32, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 64, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 128, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 2048, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": null, | |
| "rope_type": "default", | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 512, | |
| "tie_word_embeddings": true, | |
| "use_bidirectional_attention": false, | |
| "use_cache": false, | |
| "vocab_size": 262208 | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.2.0", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 64, | |
| "image_size": 16, | |
| "intermediate_size": 128, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 2, | |
| "num_channels": 3, | |
| "num_hidden_layers": 1, | |
| "patch_size": 16 | |
| } | |
| } | |