roberta_smal / config.json
Defetya's picture
smol_roberta (#1)
13c18cb
{
"_name_or_path": "/kaggle/input/xl-roberta-facebook-weights-1-shard/XL_roberta_facebook",
"architectures": [
"XLMRobertaXLForMultipleChoice"
],
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 10240,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta-xl",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"tokenizer_class": "XLMRobertaTokenizer",
"torch_dtype": "float16",
"transformers_version": "4.30.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250880
}