prompt-classification / config.json
valpy's picture
Upload DebertaV2ForSequenceClassification
9345fdc verified
raw
history blame
2.11 kB
{
"_name_or_path": "classification-testing",
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"finetuning_task": "text-classification",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "analysis or decision explanation",
"1": "assisting or creative writing",
"2": "classification",
"3": "coding",
"4": "editing or rewriting",
"5": "factual information (general or professional), history or common practices",
"6": "information extraction or summarization",
"7": "linguistics",
"8": "logical reasoning",
"9": "mathematical reasoning or calculation",
"10": "multilinguality or translation",
"11": "other",
"12": "recommendation",
"13": "roleplay",
"14": "tips, opinions or advice"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"analysis or decision explanation": 0,
"assisting or creative writing": 1,
"classification": 2,
"coding": 3,
"editing or rewriting": 4,
"factual information (general or professional), history or common practices": 5,
"information extraction or summarization": 6,
"linguistics": 7,
"logical reasoning": 8,
"mathematical reasoning or calculation": 9,
"multilinguality or translation": 10,
"other": 11,
"recommendation": 12,
"roleplay": 13,
"tips, opinions or advice": 14
},
"layer_norm_eps": 1e-07,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta-v2",
"norm_rel_ebd": "layer_norm",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 1024,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"problem_type": "single_label_classification",
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.39.0.dev0",
"type_vocab_size": 0,
"vocab_size": 128100
}