File size: 1,371 Bytes
191d1d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
{
"_name_or_path": "/home/bond005/competitions/SHROOM/models/xlm-roberta-xl-hallucination-detector",
"architectures": [
"XLMRobertaXLForHierarchicalSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"auto_map": {
"AutoConfig": "modeling_hierarchical_classifier.HierarchicalXLMRobertaXLConfig",
"AutoModelForSequenceClassification": "modeling_hierarchical_classifier.XLMRobertaXLForHierarchicalSequenceClassification",
"AutoModelForTextEncoding": "modeling_hierarchical_classifier.XLMRobertaXLForHierarchicalEmbedding"
},
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 2560,
"id2label": {
"0": "Not Hallucination",
"1": "Hallucination"
},
"initializer_range": 0.02,
"intermediate_size": 10240,
"label2id": {
"Hallucination": 1,
"Not Hallucination": 0
},
"label_smoothing": null,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "hierarchical-xlm-roberta-xl",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"temperature": 0.1,
"tokenizer_class": "XLMRobertaTokenizer",
"torch_dtype": "float32",
"transformers_version": "4.35.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250880
}
|