adaptable-fly-271 / config.json
ElMad's picture
stackoverflow_tag_classification/initial_run/deberta-v3-xsmall/adaptable-fly-271
c0b8987 verified
{
"_name_or_path": "microsoft/deberta-v3-xsmall",
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"id2label": {
"0": "python-3.x",
"1": "windows",
"2": "django",
"3": "list",
"4": "csv",
"5": "json",
"6": "numpy",
"7": "dictionary",
"8": "matplotlib",
"9": "flask",
"10": "beautifulsoup",
"11": "django-models",
"12": "multithreading",
"13": "python-2.7",
"14": "sqlalchemy",
"15": "arrays",
"16": "tkinter",
"17": "google-app-engine",
"18": "regex",
"19": "mysql",
"20": "scipy",
"21": "string",
"22": "pandas",
"23": "html",
"24": "linux"
},
"initializer_range": 0.02,
"intermediate_size": 1536,
"label2id": {
"arrays": 15,
"beautifulsoup": 10,
"csv": 4,
"dictionary": 7,
"django": 2,
"django-models": 11,
"flask": 9,
"google-app-engine": 17,
"html": 23,
"json": 5,
"linux": 24,
"list": 3,
"matplotlib": 8,
"multithreading": 12,
"mysql": 19,
"numpy": 6,
"pandas": 22,
"python-2.7": 13,
"python-3.x": 0,
"regex": 18,
"scipy": 20,
"sqlalchemy": 14,
"string": 21,
"tkinter": 16,
"windows": 1
},
"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": 6,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 384,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"problem_type": "multi_label_classification",
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.46.2",
"type_vocab_size": 0,
"vocab_size": 128100
}