Token Classification
GLiNER
PyTorch
English
entity recognition
named-entity-recognition
zero-shot
zero-shot-ner
zero shot
biomedical-nlp
cancer-genetics
oncology
gene-regulation
cancer-research
amino_acid
anatomical_system
cancer
cell
cellular_component
developing_anatomical_structure
gene_or_gene_product
immaterial_anatomical_entity
multi-tissue_structure
organ
organism
organism_subdivision
organism_substance
pathological_formation
simple_chemical
tissue
{ | |
"class_token_index": 250100, | |
"dropout": 0.3, | |
"embed_ent_token": true, | |
"encoder_config": { | |
"_name_or_path": "google/mt5-base", | |
"add_cross_attention": false, | |
"architectures": [ | |
"MT5ForConditionalGeneration" | |
], | |
"bad_words_ids": null, | |
"begin_suppress_tokens": null, | |
"bos_token_id": null, | |
"chunk_size_feed_forward": 0, | |
"classifier_dropout": 0.0, | |
"cross_attention_hidden_size": null, | |
"d_ff": 2048, | |
"d_kv": 64, | |
"d_model": 768, | |
"decoder_start_token_id": 0, | |
"dense_act_fn": "gelu_new", | |
"diversity_penalty": 0.0, | |
"do_sample": false, | |
"dropout_rate": 0.1, | |
"early_stopping": false, | |
"encoder_no_repeat_ngram_size": 0, | |
"eos_token_id": 1, | |
"exponential_decay_length_penalty": null, | |
"feed_forward_proj": "gated-gelu", | |
"finetuning_task": null, | |
"forced_bos_token_id": null, | |
"forced_eos_token_id": null, | |
"id2label": { | |
"0": "LABEL_0", | |
"1": "LABEL_1" | |
}, | |
"initializer_factor": 1.0, | |
"is_decoder": false, | |
"is_encoder_decoder": true, | |
"is_gated_act": true, | |
"label2id": { | |
"LABEL_0": 0, | |
"LABEL_1": 1 | |
}, | |
"layer_norm_epsilon": 1e-06, | |
"length_penalty": 1.0, | |
"max_length": 20, | |
"min_length": 0, | |
"model_type": "mt5", | |
"no_repeat_ngram_size": 0, | |
"num_beam_groups": 1, | |
"num_beams": 1, | |
"num_decoder_layers": 12, | |
"num_heads": 12, | |
"num_layers": 12, | |
"num_return_sequences": 1, | |
"output_attentions": false, | |
"output_hidden_states": false, | |
"output_past": true, | |
"output_scores": false, | |
"pad_token_id": 0, | |
"prefix": null, | |
"problem_type": null, | |
"pruned_heads": {}, | |
"relative_attention_max_distance": 128, | |
"relative_attention_num_buckets": 32, | |
"remove_invalid_values": false, | |
"repetition_penalty": 1.0, | |
"return_dict": true, | |
"return_dict_in_generate": false, | |
"sep_token_id": null, | |
"suppress_tokens": null, | |
"task_specific_params": null, | |
"temperature": 1.0, | |
"tf_legacy_loss": false, | |
"tie_encoder_decoder": false, | |
"tie_word_embeddings": false, | |
"tokenizer_class": "T5Tokenizer", | |
"top_k": 50, | |
"top_p": 1.0, | |
"torch_dtype": null, | |
"torchscript": false, | |
"typical_p": 1.0, | |
"use_bfloat16": false, | |
"use_cache": true, | |
"vocab_size": 250102 | |
}, | |
"ent_token": "<<ENT>>", | |
"eval_every": 10000, | |
"fine_tune": true, | |
"freeze_token_rep": false, | |
"fuse_layers": false, | |
"has_rnn": true, | |
"hidden_size": 768, | |
"label_smoothing": 0, | |
"labels_encoder": null, | |
"labels_encoder_config": null, | |
"log_dir": "models/", | |
"loss_alpha": 0.75, | |
"loss_gamma": 0, | |
"loss_reduction": "sum", | |
"lr_encoder": "1e-5", | |
"lr_others": "3e-5", | |
"max_grad_norm": 10.0, | |
"max_len": 1024, | |
"max_neg_type_ratio": 1, | |
"max_types": 30, | |
"max_width": 12, | |
"model_name": "google/mt5-base", | |
"model_type": "gliner", | |
"name": "span level gliner", | |
"num_post_fusion_layers": 1, | |
"num_steps": 80000, | |
"post_fusion_schema": "", | |
"prev_path": null, | |
"random_drop": true, | |
"root_dir": "gliner_logs", | |
"save_total_limit": 3, | |
"scheduler_type": "cosine", | |
"sep_token": "<<SEP>>", | |
"shuffle_types": true, | |
"size_sup": -1, | |
"span_mode": "markerV0", | |
"subtoken_pooling": "first", | |
"train_batch_size": 8, | |
"train_data": "data/multilingual_data.json", | |
"transformers_version": "4.43.4", | |
"val_data_dir": "none", | |
"vocab_size": 250102, | |
"warmup_ratio": 0.05, | |
"weight_decay_encoder": 0.1, | |
"weight_decay_other": 0.01, | |
"words_splitter_type": "universal" | |
} | |