Update from fl418

README.md

@@ -0,0 +1,20 @@
+---
+language: en
+
+tags:
+- word-embeddings
+- word-similarity
+
+### mirror-bert-base-uncased-word
+An unsupervised word encoder proposed by [Liu et al. (2021)](https://arxiv.org/pdf/2104.08027.pdf). Trained with a set of unlabelled words, using [bert-base-uncased](https://huggingface.co/bert-base-uncased) as the base model. Please use `[CLS]` as the representation of the input.
+
+### Citation
+```bibtex
+@inproceedings{
+	liu2021fast,
+  title={Fast, Effective and Self-Supervised: Transforming Masked LanguageModels into Universal Lexical and Sentence Encoders},
+  author={Liu, Fangyu and Vuli{\'c}, Ivan and Korhonen, Anna and Collier, Nigel},
+  booktitle={EMNLP 2021},
+  year={2021}
+}
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.2.1",
+  "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:da971a92c79bc2e05e0d15f80a31231273f2b82a9b065867c13d0ba2a37fb209
+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, "model_max_length": 512, "name_or_path": "bert-base-uncased"}