Updated model with better training and evaluation. Test and val data included as pickle files. Older Legacy files were removed to avoid confusion.
034082e
| { | |
| "_name_or_path": "oshizo/sbert-jsnli-luke-japanese-base-lite", | |
| "architectures": [ | |
| "LukeModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bert_model_name": "models/luke-japanese/hf_xlm_roberta", | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "cls_entity_prediction": false, | |
| "entity_emb_size": 256, | |
| "entity_vocab_size": 4, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "luke", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.1", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "use_entity_aware_attention": true, | |
| "vocab_size": 32772 | |
| } | |