| { |
| "_name_or_path": "/lm_models/excell-roberta/v3-training-512bs/checkpoint-2716290", |
| "architectures": [ |
| "EXcellRobertaForTokenClassification" |
| ], |
| "attention_probs_dropout_prob": 0.2, |
| "bias_dense_layers": false, |
| "bias_norm": false, |
| "bos_token_id": 0, |
| "classifier_dropout": null, |
| "dense_layer_bias": false, |
| "eos_token_id": 1, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.2, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "O", |
| "1": "B-PANEL_START", |
| "2": "I-PANEL_START" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "B-PANEL_START": 1, |
| "I-PANEL_START": 2, |
| "O": 0 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 514, |
| "model_type": "roberta", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 3, |
| "position_embedding_type": "absolute", |
| "return_dict": false, |
| "sep_token_id": 1, |
| "swiglu": true, |
| "swiglu_reduction": 2, |
| "tokenizer_class": "RobertaTokenizerFast", |
| "torch_dtype": "float32", |
| "transformers_version": "4.20.0", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 64000 |
| } |
|
|
