add model

.gitattributes

@@ -25,3 +25,4 @@
 ./clr/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
 ./adsbert/v5/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
 ./detection/PascalVOC_Detection/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+./culr/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

culr/README.md

@@ -0,0 +1,31 @@
+## 9/13/2021
+Junyi: repackage CULRv2 using config from InfoXLM from Huggingface as these two models are the same
+
+# InfoXLM
+
+**InfoXLM** (NAACL 2021, [paper](https://arxiv.org/pdf/2007.07834.pdf), [repo](https://github.com/microsoft/unilm/tree/master/infoxlm), [model](https://huggingface.co/microsoft/infoxlm-base)) InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training.
+
+**MD5**
+
+```
+05b95b7d977450b364f8ea3269391953  config.json
+c19438359fed6d36b0c1bbb107929579  pytorch_model.bin
+bf25eb5120ad92ef5c7d8596b5dc4046  sentencepiece.bpe.model
+eedbd60a7268b9fc45981b849664f747  tokenizer.json
+```
+
+**BibTeX**
+
+```
+@inproceedings{chi-etal-2021-infoxlm,
+  title = "{I}nfo{XLM}: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training",
+  author={Chi, Zewen and Dong, Li and Wei, Furu and Yang, Nan and Singhal, Saksham and Wang, Wenhui and Song, Xia and Mao, Xian-Ling and Huang, Heyan and Zhou, Ming},
+  booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
+  month = jun,
+  year = "2021",
+  address = "Online",
+  publisher = "Association for Computational Linguistics",
+  url = "https://aclanthology.org/2021.naacl-main.280",
+  doi = "10.18653/v1/2021.naacl-main.280",
+  pages = "3576--3588",}
+```

culr/config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 250008
+}

culr/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449a9d7026fd3bc28a96134a0f44f92cb4d2479fe1d0ff79d77681880ed5ce10
+size 2241874340

culr/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051