| { | |
| "architectures": [ | |
| "UMT5ForTokenClassification" | |
| ], | |
| "bos_token_id": 2, | |
| "classifier_dropout": 0.0, | |
| "d_ff": 37, | |
| "d_kv": 8, | |
| "d_model": 32, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 0.002, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "umt5", | |
| "num_decoder_layers": 2, | |
| "num_heads": 4, | |
| "num_layers": 2, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 8, | |
| "tokenizer_class": "T5Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 1506 | |
| } | |