| { |
| "_name_or_path": "mahdibaghbanzadeh/seqsight_16384_512_56M", |
| "architectures": [ |
| "DebertaV2ForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "cls_token_id": 3, |
| "eos_token_id": 1, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-07, |
| "max_position_embeddings": 512, |
| "max_relative_positions": -1, |
| "model_type": "deberta-v2", |
| "num_attention_heads": 6, |
| "num_hidden_layers": 6, |
| "pad_token_id": 2, |
| "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": "4.38.2", |
| "type_vocab_size": 0, |
| "vocab_size": 16384 |
| } |
|
|
