| { |
| "architectures": [ |
| "PaliGemmaForConditionalGeneration" |
| ], |
| "bos_token_id": 2, |
| "dtype": "bfloat16", |
| "eos_token_id": 1, |
| "hidden_size": 2048, |
| "ignore_index": -100, |
| "image_token_index": 257152, |
| "model_type": "paligemma", |
| "pad_token_id": 0, |
| "projection_dim": 2048, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "head_dim": 256, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_activation": null, |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "max_position_embeddings": 8192, |
| "model_type": "gemma", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 18, |
| "num_image_tokens": 1024, |
| "num_key_value_heads": 1, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 10000.0, |
| "use_cache": true, |
| "vocab_size": 257216 |
| }, |
| "transformers_version": "4.57.3", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "image_size": 448, |
| "intermediate_size": 4304, |
| "layer_norm_eps": 1e-06, |
| "model_type": "siglip_vision_model", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 27, |
| "num_image_tokens": 1024, |
| "patch_size": 14, |
| "projection_dim": 2048, |
| "projector_hidden_act": "gelu_fast", |
| "vision_use_head": false |
| } |
| } |
|
|