init

README.md

@@ -0,0 +1,33 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- feature-extraction
+- sentence-similarity
+- transformers
+---
+
+# CoT-MAE base uncased
+
+CoT-MAE is a transformers based Mask Auto-Encoder pretraining architecture designed for Dense Passage Retrieval.
+**CoT-MAE base uncased** is a general pre-training language model trained with unsupervised MS-Marco corpus.
+
+Details can be found in our paper and codes.
+
+Paper: [ConTextual Mask Auto-Encoder for Dense Passage Retrieval](https://arxiv.org/abs/2208.07670).
+
+Code: [caskcsg/ir/cotmae](https://github.com/caskcsg/ir/tree/main/cotmae)
+
+## Citations
+If you find our work useful, please cite our paper.
+```bibtex
+@misc{https://doi.org/10.48550/arxiv.2208.07670,
+  doi = {10.48550/ARXIV.2208.07670},
+  url = {https://arxiv.org/abs/2208.07670},
+  author = {Wu, Xing and Ma, Guangyuan and Lin, Meng and Lin, Zijia and Wang, Zhongyuan and Hu, Songlin},
+  keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences},
+  title = {ConTextual Mask Auto-Encoder for Dense Passage Retrieval},
+  publisher = {arXiv},
+  year = {2022},
+  copyright = {arXiv.org perpetual, non-exclusive license}
+}
+```

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "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": "4.2.0",
+  "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 sha256:7765d395ef3b7d08d6b66af55fa9dfcd0b9aa48025a6c4a51516ff3b6c858efe
+size 438147282

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}