|
{ |
|
"class_token_index": 128002, |
|
"dropout": 0.4, |
|
"embed_ent_token": true, |
|
"encoder_config": { |
|
"_name_or_path": "microsoft/deberta-v3-small", |
|
"add_cross_attention": false, |
|
"architectures": null, |
|
"attention_probs_dropout_prob": 0.1, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_eps": 1e-07, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"max_position_embeddings": 512, |
|
"max_relative_positions": -1, |
|
"min_length": 0, |
|
"model_type": "deberta-v2", |
|
"no_repeat_ngram_size": 0, |
|
"norm_rel_ebd": "layer_norm", |
|
"num_attention_heads": 12, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_hidden_layers": 6, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": 0, |
|
"pooler_dropout": 0, |
|
"pooler_hidden_act": "gelu", |
|
"pooler_hidden_size": 768, |
|
"pos_att_type": [ |
|
"p2c", |
|
"c2p" |
|
], |
|
"position_biased_input": false, |
|
"position_buckets": 256, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"relative_attention": true, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"share_att_key": true, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": null, |
|
"torchscript": false, |
|
"type_vocab_size": 0, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"vocab_size": 128004 |
|
}, |
|
"ent_token": "<<ENT>>", |
|
"eval_every": 5000, |
|
"fine_tune": true, |
|
"fuse_layers": false, |
|
"has_rnn": true, |
|
"hidden_size": 512, |
|
"labels_encoder": null, |
|
"labels_encoder_config": null, |
|
"lr_encoder": "1e-5", |
|
"lr_others": "5e-5", |
|
"max_len": 384, |
|
"max_neg_type_ratio": 1, |
|
"max_types": 25, |
|
"max_width": 12, |
|
"model_name": "microsoft/deberta-v3-small", |
|
"model_type": "gliner", |
|
"name": "correct", |
|
"num_post_fusion_layers": 1, |
|
"num_steps": 30000, |
|
"post_fusion_schema": "", |
|
"random_drop": true, |
|
"sep_token": "<<SEP>>", |
|
"shuffle_types": true, |
|
"size_sup": -1, |
|
"span_mode": "markerV0", |
|
"subtoken_pooling": "first", |
|
"train_batch_size": 8, |
|
"transformers_version": "4.44.2", |
|
"vocab_size": 128004, |
|
"warmup_ratio": 3000, |
|
"words_splitter_type": "whitespace" |
|
} |
|
|