|
{ |
|
"_name_or_path": "/cluster/home/tialiu/project_tianyu/projects/generative-coref/t0_3b", |
|
"architectures": [ |
|
"T5Coref" |
|
], |
|
"asp_activation": "relu", |
|
"asp_dropout_rate": 0.3, |
|
"asp_feature_emb_size": 20, |
|
"asp_hidden_dim": 4096, |
|
"asp_init_std": 0.02, |
|
"d_ff": 5120, |
|
"d_kv": 64, |
|
"d_model": 2048, |
|
"decoder_start_token_id": 0, |
|
"dense_act_fn": "gelu_new", |
|
"dropout_rate": 0.1, |
|
"eos_token_id": 1, |
|
"feed_forward_proj": "gated-gelu", |
|
"gradient_checkpointing": false, |
|
"initializer_factor": 1.0, |
|
"is_encoder_decoder": true, |
|
"is_gated_act": true, |
|
"layer_norm_epsilon": 1e-06, |
|
"mention_end_id": 32103, |
|
"mention_start_id": 32102, |
|
"model_type": "t5", |
|
"num_decoder_layers": 24, |
|
"num_heads": 32, |
|
"num_layers": 24, |
|
"output_past": true, |
|
"pad_token_id": 0, |
|
"pretrained_name_or_path": "/cluster/home/tialiu/tianyu/huggingface_models//T0_3B", |
|
"relative_attention_max_distance": 128, |
|
"relative_attention_num_buckets": 32, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.23.1", |
|
"use_cache": true, |
|
"vocab_size": 32104 |
|
} |
|
|