lhbonifacio commited on
Commit
a9c0d68
1 Parent(s): c4e5c83

Initial commit for v2

Browse files
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: pt
3
+ license: mit
4
+ tags:
5
+ - msmarco
6
+ - miniLM
7
+ - pytorch
8
+ - tensorflow
9
+ - pt
10
+ - pt-br
11
+ datasets:
12
+ - msmarco
13
+ widget:
14
+ - text: "Texto de exemplo em português"
15
+ inference: false
16
+ ---
17
+ # mMiniLM-L6-v2 Reranker finetuned on mMARCO
18
+ ## Introduction
19
+ mMiniLM-L6-v2-pt-msmarco-v2 is a multilingual miniLM-based model finetuned on a Portuguese translated version of MS MARCO passage dataset. In the v2 version, the Portuguese dataset was translated using Google Translate.
20
+ Further information about the dataset or the translation method can be found on our [**mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset**](https://arxiv.org/abs/2108.13897) and [mMARCO](https://github.com/unicamp-dl/mMARCO) repository.
21
+ ## Usage
22
+ ```python
23
+ from transformers import AutoTokenizer, AutoModel
24
+
25
+ model_name = 'unicamp-dl/mMiniLM-L6-v2-pt-msmarco-v1'
26
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
27
+ model = AutoModel.from_pretrained(model_name)
28
+
29
+ ```
30
+ # Citation
31
+ If you use mMiniLM-L6-v2-pt-msmarco-v2, please cite:
32
+
33
+ @misc{bonifacio2021mmarco,
34
+ title={mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset},
35
+ author={Luiz Henrique Bonifacio and Vitor Jeronymo and Hugo Queiroz Abonizio and Israel Campiotti and Marzieh Fadaee and and Roberto Lotufo and Rodrigo Nogueira},
36
+ year={2021},
37
+ eprint={2108.13897},
38
+ archivePrefix={arXiv},
39
+ primaryClass={cs.CL}
40
+ }
41
+
42
+
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./data/mMiniLM-L6-H384-distilled-from-XLMR-Large/",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": 384,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1536,
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": 6,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.11.3",
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:b0fc25356518b3c6bc8aa48a2af3b5ad5639938140795c5af618341ccbbc2120
3
+ size 428023405
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": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "./data/mMiniLM-L6-H384-distilled-from-XLMR-Large/", "tokenizer_class": "XLMRobertaTokenizer"}