{ "prismer_base": { "roberta_model": { "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "vision_hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_name": "roberta-base", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "type_vocab_size": 1, "vocab_size": 50265, "num_decoder_layers": 4, "is_decoder": true }, "vit_model": "ViT-B/16" }, "prismer_large": { "roberta_model": { "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "vision_hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_name": "roberta-large", "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 1, "type_vocab_size": 1, "vocab_size": 50265, "num_decoder_layers": 4, "is_decoder": true }, "vit_model": "ViT-L/14@336px" }, "prismer_huge": { "roberta_model": { "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "vision_hidden_size": 1280, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_name": "roberta-large", "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 1, "type_vocab_size": 1, "vocab_size": 50265, "num_decoder_layers": 4, "is_decoder": true }, "vit_model": "ViT-H/14" } }