usclm-robrta-base-mk1 / config.json
gabrielaltay's picture
Training in progress, step 2024
6597951 verified
raw
history blame contribute delete
643 Bytes
{
"architectures": [
"RobertaForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 1026,
"model_type": "roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.39.0.dev0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 50265
}