Lauler's picture
v2.0 with teacher all-mpnet-base-v2, trained with longer paragraphs
a65f4bc
raw
history blame contribute delete
710 Bytes
{
"_name_or_path": "output/no-normalize-en-sv-2022-12-26_18-39-42/",
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"gradient_checkpointing": false,
"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": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.25.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 50325
}