Initial commit for v2

README.md

@@ -0,0 +1,42 @@
+---
+language: pt
+license: mit
+tags:
+- msmarco
+- t5
+- pytorch
+- tensorflow
+- pt
+- pt-br
+datasets:
+- msmarco
+widget:
+- text: "Texto de exemplo em português"
+inference: false
+---
+# mt5-base Reranker finetuned on mMARCO
+## Introduction
+mt5-base-mmarco-v2 is a mT5-based model fine-tuned on a multilingual translated version of MS MARCO passage dataset. This dataset, named Multi MS MARCO, is formed by 9 complete MS MARCO passages collection in 9 different languages.  In the v2 version, the datasets were translated using Google Translate.
+Further information about the dataset or the translation method can be found on our paper [**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 T5Tokenizer, MT5ForConditionalGeneration
+
+model_name = 'unicamp-dl/mt5-base-mmarco-v2'
+tokenizer  = T5Tokenizer.from_pretrained(model_name)
+model      = MT5ForConditionalGeneration.from_pretrained(model_name)
+
+```
+# Citation
+If you use mt5-base-mmarco-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  and Roberto Lotufo and Rodrigo Nogueira},
+      year={2021},
+      eprint={2108.13897},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "mt5_base_mmarco/",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e2ae2eae6f9be089eb56416ee3419a41e4f5a1e82515e15e78d67e1ef5be36
+size 2329696333

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-base", "tokenizer_class": "T5Tokenizer"}