{ "_attn_implementation_autoset": true, "_name_or_path": "optimum-internal-testing/tiny-random-PaliGemmaForConditionalGeneration", "_vocab_size": 257152, "architectures": [ "PaliGemmaForConditionalGeneration" ], "hidden_size": 2048, "image_token_index": 0, "model_type": "paligemma", "projection_dim": 32, "projector_hidden_act": "gelu", "text_config": { "attention_probs_dropout_prob": 0.1, "head_dim": 8, "hidden_activation": "gelu_pytorch_tanh", "hidden_dropout_prob": 0.1, "hidden_size": 32, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "intermediate_size": 37, "is_training": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "max_position_embeddings": 512, "model_type": "gemma", "num_attention_heads": 4, "num_choices": 4, "num_hidden_layers": 2, "num_image_tokens": 16, "num_key_value_heads": 1, "pad_token_id": 1, "seq_length": 264, "type_sequence_label_size": 2, "type_vocab_size": 16, "use_labels": true, "use_token_type_ids": false, "vocab_size": 257153 }, "torch_dtype": "float32", "transformers_version": "4.48.0.dev0", "vision_config": { "attention_dropout": 0.1, "dropout": 0.1, "hidden_size": 32, "image_size": 20, "initializer_range": 0.02, "intermediate_size": 37, "is_training": true, "model_type": "siglip_vision_model", "num_attention_heads": 4, "num_hidden_layers": 2, "num_image_tokens": 4, "num_key_value_heads": 1, "patch_size": 5, "projection_dim": 32, "use_labels": true }, "vision_feature_layer": -1, "vision_feature_select_strategy": "default", "num_image_tokens": 16 }