Initial commit for v2

README.md

@@ -0,0 +1,40 @@
+---
+language: pt
+license: mit
+tags:
+- msmarco
+- miniLM
+- pytorch
+- tensorflow
+- pt
+- pt-br
+datasets:
+- msmarco
+widget:
+- text: "Texto de exemplo em português"
+inference: false
+---
+# mMiniLM-L6-v2 Reranker finetuned on mMARCO
+## Introduction
+mMiniLM-L6-v2-en-pt-msmarco-v2 is a multilingual miniLM-based model finetuned on a bilingual version of MS MARCO passage dataset. This bilingual dataset version is formed by the original MS MARCO dataset (in English) and a Portuguese translated version.  In the v2 version, the Portuguese dataset was translated using Google Translate.
+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.
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModel
+
+model_name = 'unicamp-dl/mMiniLM-L6-v2-en-pt-msmarco-v2'
+tokenizer  = AutoTokenizer.from_pretrained(model_name)
+model      = AutoModel.from_pretrained(model_name)
+
+```
+# Citation
+If you use mMiniLM-L6-v2-en-pt-msmarco-v2, please cite:
+
+    @misc{bonifacio2021mmarco,
+      title={mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset}, 
+      author={Luiz Henrique Bonifacio and Vitor Jeronymo and Hugo Queiroz Abonizio and Israel Campiotti and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
+      year={2021},
+      eprint={2108.13897},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "./data/mMiniLM-L6-H384-distilled-from-XLMR-Large/",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71bfa862091da6f3d70f6782bc72e47657afdb24abf051cbfb3ae4b3b5b8022
+size 428023405

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +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_config.json

@@ -0,0 +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"}