{ "_name_or_path": "ul2_model", "architectures": [ "T5ForConditionalGeneration" ], "d_ff": 16384, "d_kv": 256, "d_model": 4096, "decoder_start_token_id": 0, "dense_act_fn": "silu", "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "gated-silu", "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": true, "layer_norm_epsilon": 1e-06, "model_type": "t5", "n_positions": 512, "num_decoder_layers": 32, "num_heads": 16, "num_layers": 32, "output_past": true, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "torch_dtype": "bfloat16", "transformers_version": "4.20.0.dev0", "use_cache": true, "vocab_size": 32128 }