| { | |
| "_name_or_path": "/home/ubuntu/utah/babylm-24/data/training/models/10M_babylm_ascii/SPM-Unigram_6144/DebertaV2-Base-10M_babylm-A", | |
| "architectures": [ | |
| "DebertaV2ForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "label2id": { | |
| "0": 0, | |
| "1": 1, | |
| "2": 2 | |
| }, | |
| "layer_norm_eps": 1e-07, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta-v2", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 8, | |
| "pad_token_id": 3, | |
| "pooler_dropout": 0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 768, | |
| "pos_att_type": null, | |
| "position_biased_input": true, | |
| "relative_attention": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.2", | |
| "type_vocab_size": 0, | |
| "vocab_size": 6144 | |
| } | |