roberta / config.json
autosyrup's picture
Training in progress, epoch 1
1b1b168
raw
history blame
888 Bytes
{
"_name_or_path": "Jean-Baptiste/roberta-large-ner-english",
"architectures": [
"RobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "O",
"1": "B-Skill",
"2": "I-Skill"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"B-Skill": 1,
"I-Skill": 2,
"O": 0
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 50265
}