| { | |
| "_name_or_path": "cliang1453/deberta-v3-xsmall-sst2-student-stage1", | |
| "architectures": [ | |
| "TEDDebertaV2ForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "filter_disabled": false, | |
| "filter_interval": 1, | |
| "filter_nonlinear": false, | |
| "filter_output_dim": 768, | |
| "finetuning_task": "sst2", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 384, | |
| "id2label": { | |
| "0": "negative", | |
| "1": "positive" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "label2id": { | |
| "negative": 0, | |
| "positive": 1 | |
| }, | |
| "layer_norm_eps": 1e-07, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "ted-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, | |
| "relative_attention": true, | |
| "share_att_key": true, | |
| "torch_dtype": "float32", | |
| "train_filters": false, | |
| "transformers_version": "4.28.0", | |
| "type_vocab_size": 0, | |
| "vocab_size": 128100 | |
| } | |