Initial commit

README.md

@@ -0,0 +1,28 @@
+---
+language: 
+  - en
+license: apache-2.0
+
+tags:
+- bert
+- biomedical
+
+---
+CODER: Knowledge infused cross-lingual medical term embedding for term normalization.
+English Version. Old name. This model is not UMLSBert!!!
+
+Github Link: https://github.com/GanjinZero/CODER
+
+```
+@article{YUAN2022103983,
+title = {CODER: Knowledge-infused cross-lingual medical term embedding for term normalization},
+journal = {Journal of Biomedical Informatics},
+pages = {103983},
+year = {2022},
+issn = {1532-0464},
+doi = {https://doi.org/10.1016/j.jbi.2021.103983},
+url = {https://www.sciencedirect.com/science/article/pii/S1532046421003129},
+author = {Zheng Yuan and Zhengyun Zhao and Haixia Sun and Jiao Li and Fei Wang and Sheng Yu},
+keywords = {medical term normalization, cross-lingual, medical term representation, knowledge graph embedding, contrastive learning}
+}
+```

config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861fbd45c0ae6b463637480bcf0e4da63f5bbded56d28b8d5b9bcee8a0153999
+size 437955508

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c22bf0346d1e5b5a1911ffdfe20a90662e21952880885c4f5ff19957f1cf470
+size 438012727