First version of the sapbert-mean-token model and tokenizer.

README.md

@@ -0,0 +1,24 @@
+---
+language: en
+
+tags:
+- biomedical
+- lexical-semantics
+
+datasets:
+- UMLS
+
+[news] SapBERT will appear in the conference proceedings of NAACL 2021!
+
+### SapBERT-PubMedBERT
+SapBERT by [Liu et al. (2020)](https://arxiv.org/pdf/2010.11784.pdf). Trained with [UMLS](https://www.nlm.nih.gov/research/umls/licensedcontent/umlsknowledgesources.html) 2020AA (English only), using [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) as the base model. Please use the mean-pooling of the output as the representation.
+
+### Citation
+```bibtex
+@article{liu2020self,
+  title={Self-alignment Pre-training for Biomedical Entity Representations},
+  author={Liu, Fangyu and Shareghi, Ehsan and Meng, Zaiqiao and Basaldella, Marco and Collier, Nigel},
+  journal={arXiv preprint arXiv:2010.11784},
+  year={2020}
+}
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.4.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b082bee075d5ecba9f7524d9de4ac7c5b2097f42d1689bc5a892bc6a16c80847
+size 438015479

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext", "do_basic_tokenize": true, "never_split": null}