ke-lly-d's picture
Initial model push
c4c0488
raw
history blame
1.28 kB
{
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "Coda",
"1": "Confluence",
"2": "GitHub",
"3": "Gmail",
"4": "Google Docs",
"5": "Google Sheets",
"6": "Google Slides",
"7": "Jira",
"8": "Miro",
"9": "Slack"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Coda": 0,
"Confluence": 1,
"GitHub": 2,
"Gmail": 3,
"Google Docs": 4,
"Google Sheets": 5,
"Google Slides": 6,
"Jira": 7,
"Miro": 8,
"Slack": 9
},
"layer_norm_eps": 1e-07,
"legacy": true,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta-v2",
"norm_rel_ebd": "layer_norm",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 768,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.52.4",
"type_vocab_size": 0,
"vocab_size": 128100
}