basilepp19/cpv-it5-base

1{2  "_name_or_path": "gsarti/it5-base",3  "architectures": [4    "T5ForConditionalGeneration"5  ],6  "d_ff": 2048,7  "d_kv": 64,8  "d_model": 768,9  "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  "gradient_checkpointing": false,15  "initializer_factor": 1.0,16  "is_encoder_decoder": true,17  "is_gated_act": true,18  "layer_norm_epsilon": 1e-06,19  "model_type": "t5",20  "num_decoder_layers": 12,21  "num_heads": 12,22  "num_layers": 12,23  "output_past": true,24  "pad_token_id": 0,25  "relative_attention_max_distance": 128,26  "relative_attention_num_buckets": 32,27  "tie_word_embeddings": false,28  "torch_dtype": "float32",29  "transformers_version": "4.26.1",30  "use_cache": true,31  "vocab_size": 3210332}33