Updated term exists model trained on multiple corpora.

added_tokens.json

@@ -0,0 +1,10 @@
+{
+  "</a1>": 28898,
+  "</a2>": 28900,
+  "</e>": 28896,
+  "<a1>": 28897,
+  "<a2>": 28899,
+  "<cr>": 28901,
+  "<e>": 28895,
+  "<neg>": 28902
+}

config.json

@@ -0,0 +1,115 @@
+{
+  "architectures": [
+    "CnlpModelForClassification"
+  ],
+  "cnlpt_version": "0.6.0",
+  "encoder_config": {
+    "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-large-uncased-abstract",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "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,
+    "eos_token_ids": 0,
+    "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": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": 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,
+    "transformers_version": "4.22.2",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 28903
+  },
+  "encoder_name": "microsoft/BiomedNLP-PubMedBERT-large-uncased-abstract",
+  "finetuning_task": [
+    "TermExists"
+  ],
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "hier_head_config": null,
+  "label_dictionary": {
+    "TermExists": [
+      "-1",
+      "1"
+    ]
+  },
+  "layer": 12,
+  "model_type": "cnlpt",
+  "num_rel_attention_heads": 12,
+  "rel_attention_head_dims": 64,
+  "relations": {
+    "TermExists": false
+  },
+  "tagger": {
+    "TermExists": false
+  },
+  "tokens": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "use_prior_tasks": false,
+  "vocab_size": 28903
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229a8317a7e60f39c797365e79f42ef89c3e2256eb50456b5d1a5969b71cd3df
+size 1338283453

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    "<e>",
+    "</e>",
+    "<a1>",
+    "</a1>",
+    "<a2>",
+    "</a2>",
+    "<cr>",
+    "<neg>"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "add_prefix_space": true,
+  "additional_special_tokens": [
+    "<e>",
+    "</e>",
+    "<a1>",
+    "</a1>",
+    "<a2>",
+    "</a2>",
+    "<cr>",
+    "<neg>"
+  ],
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "microsoft/BiomedNLP-PubMedBERT-large-uncased-abstract",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}