acdsd/DDI
026
1{2 "architectures": [3 "FSDPT5ForConditionalGeneration"4 ],5 "classifier_dropout": 0.0,6 "d_ff": 2816,7 "d_kv": 64,8 "d_model": 1024,9 "decoder_start_token_id": 0,10 "dense_act_fn": "gelu_new",11 "dropout_rate": 0.1,12 "eos_token_id": 1,13 "feed_forward_proj": "gated-gelu",14 "initializer_factor": 1.0,15 "is_encoder_decoder": true,16 "is_gated_act": true,17 "layer_norm_epsilon": 1e-06,18 "model_type": "t5",19 "num_decoder_layers": 24,20 "num_heads": 16,21 "num_layers": 24,22 "output_past": true,23 "pad_token_id": 0,24 "relative_attention_max_distance": 128,25 "relative_attention_num_buckets": 32,26 "tie_word_embeddings": false,27 "torch_dtype": "float32",28 "transformers_version": "4.53.3",29 "use_cache": true,30 "vocab_size": 3210231}32 