Gaanaman's picture
Initial upload: DeBERTa-v2-xlarge (Epoch 3)
c51dfc5 verified
Raw
History Blame Contribute Delete
1.7 kB
{
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_head_size": 64,
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 1,
"conv_act": "gelu",
"conv_kernel_size": 3,
"dtype": "float32",
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1536,
"id2label": {
"0": "ad hominem",
"1": "anecdote",
"2": "cherry picking",
"3": "conspiracy theory",
"4": "fake experts",
"5": "false choice",
"6": "false equivalence",
"7": "impossible expectations",
"8": "misrepresentation",
"9": "oversimplification",
"10": "single cause",
"11": "slothful induction"
},
"initializer_range": 0.02,
"intermediate_size": 6144,
"label2id": {
"ad hominem": 0,
"anecdote": 1,
"cherry picking": 2,
"conspiracy theory": 3,
"fake experts": 4,
"false choice": 5,
"false equivalence": 6,
"impossible expectations": 7,
"misrepresentation": 8,
"oversimplification": 9,
"single cause": 10,
"slothful induction": 11
},
"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": 24,
"num_hidden_layers": 24,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 1536,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"problem_type": "single_label_classification",
"relative_attention": true,
"share_att_key": true,
"transformers_version": "4.57.3",
"type_vocab_size": 0,
"vocab_size": 128100
}