asparius/electra-small-initial
07
1{2 "_name_or_path": "electra-pytorch/output/pretrain/2023-04-25-23-21-44/ckpt/10000/tokenizer_bert-base-uncased_8192vocab_10M/",3 "architectures": [4 "ElectraModel"5 ],6 "attention_probs_dropout_prob": 0.1,7 "classifier_dropout": null,8 "embedding_size": 128,9 "hidden_act": "gelu",10 "hidden_dropout_prob": 0.1,11 "hidden_size": 256,12 "initializer_range": 0.02,13 "intermediate_size": 1024,14 "layer_norm_eps": 1e-12,15 "max_position_embeddings": 512,16 "model_type": "electra",17 "num_attention_heads": 4,18 "num_hidden_layers": 12,19 "pad_token_id": 0,20 "position_embedding_type": "absolute",21 "summary_activation": "gelu",22 "summary_last_dropout": 0.1,23 "summary_type": "first",24 "summary_use_proj": true,25 "torch_dtype": "float32",26 "transformers_version": "4.25.1",27 "type_vocab_size": 2,28 "use_cache": true,29 "vocab_size": 3052230}31 