vince62s commited on
Commit
86bc315
1 Parent(s): 5dd2265

Upload 5 files

Browse files
Files changed (5) hide show
  1. README.md +28 -3
  2. config.json +22 -0
  3. pytorch_model.bin +3 -0
  4. sentencepiece.bpe.model +3 -0
  5. tokenizer.json +0 -0
README.md CHANGED
@@ -1,3 +1,28 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # InfoXLM
2
+
3
+ **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.
4
+
5
+ **MD5**
6
+
7
+ ```
8
+ 05b95b7d977450b364f8ea3269391953 config.json
9
+ c19438359fed6d36b0c1bbb107929579 pytorch_model.bin
10
+ bf25eb5120ad92ef5c7d8596b5dc4046 sentencepiece.bpe.model
11
+ eedbd60a7268b9fc45981b849664f747 tokenizer.json
12
+ ```
13
+
14
+ **BibTeX**
15
+
16
+ ```
17
+ @inproceedings{chi-etal-2021-infoxlm,
18
+ title = "{I}nfo{XLM}: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training",
19
+ 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},
20
+ booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
21
+ month = jun,
22
+ year = "2021",
23
+ address = "Online",
24
+ publisher = "Association for Computational Linguistics",
25
+ url = "https://aclanthology.org/2021.naacl-main.280",
26
+ doi = "10.18653/v1/2021.naacl-main.280",
27
+ pages = "3576--3588",}
28
+ ```
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 514,
15
+ "model_type": "xlm-roberta",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "output_past": true,
19
+ "pad_token_id": 1,
20
+ "type_vocab_size": 1,
21
+ "vocab_size": 250002
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9851dca7395338e75587c6e869542cd7cc23159c9b3e4e0e65e7303a672aeb5
3
+ size 1130454122
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff