{ "_name_or_path": "/project/6007993/elmadany/T5/ArT5_models/MSA_1M_small", "d_ff": 1024, "d_kv": 64, "d_model": 512, "decoder_start_token_id": 0, "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "gated-gelu", "gradient_checkpointing": false, "initializer_factor": 1.0, "is_encoder_decoder": true, "layer_norm_epsilon": 1e-06, "model_type": "t5", "num_decoder_layers": 12, "num_heads": 6, "num_layers": 8, "output_past": true, "pad_token_id": 0, "relative_attention_num_buckets": 32, "transformers_version": "4.9.2", "use_cache": true, "vocab_size": 110080 }