eugene-yang commited on
Commit
513f6f4
1 Parent(s): de32a44

commit model

Browse files
README.md CHANGED
@@ -1,3 +1,17 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+ DPR Model with XLM-Align trained with MSMARCO.
6
+
7
+ Please consider citing the following paper if you use this model.
8
+
9
+ ```
10
+ @inproceedings{sigir2022c3,
11
+ author = {Eugene Yang and Suraj Nair and Ramraj Chandradevan and Rebecca Iglesias-Flores and Douglas W. Oard},
12
+ title = {C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval},
13
+ booktitle = {Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (Short Paper)},
14
+ year = {2022},
15
+ url = {https://arxiv.org/abs/2204.11989}
16
+ }
17
+ ```
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/xlm-align-base",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 514,
23
+ "model_type": "xlm-roberta",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 1,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.13.0",
31
+ "type_vocab_size": 1,
32
+ "use_cache": true,
33
+ "vocab_size": 250002
34
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74428a4fbfbf711d18e4d22a840df72b9a354fa35d15e41914f9be77ab1b4b3
3
+ size 1112255985
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": "/home/hltcoe/eyang/.cache/huggingface/transformers/cbe31e6cd45dd68473922e1e37a32a6f3d8061e7affd24feaed6fb32a4c6ab30.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "microsoft/xlm-align-base", "tokenizer_class": "XLMRobertaTokenizer"}