Upload folder using huggingface_hub

README.md

@@ -0,0 +1,47 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- en
+- de
+- fr
+- zh
+- ja
+- ro
+tags:
+- word alignment
+- multilingual
+- translation
+---
+# Model Description 
+Refer to [https://github.com/qiyuw/WSPAlign](https://github.com/qiyuw/WSPAlign) and [https://github.com/qiyuw/WSPAlign.InferEval](https://github.com/qiyuw/WSPAlign.InferEval) for details.
+
+# Qucik Usage
+
+First clone inference repository:
+```
+git clone https://github.com/qiyuw/WSPAlign.InferEval.git
+```
+Then install the requirements following [https://github.com/qiyuw/WSPAlign.InferEval](https://github.com/qiyuw/WSPAlign.InferEval). For inference only `transformers`, `SpaCy` and `torch` are required.
+
+Finally, run the following example:
+```
+python inference.py --model_name_or_path qiyuw/WSPAlign-ft-kftt --src_lang ja --src_text="私は猫が好きです。" --tgt_lang en --tgt_text="I like cats."
+```
+Check `inference.py` for details usage.
+
+# Citation
+Cite our paper if WSPAlign helps your work:
+
+```bibtex
+@inproceedings{wu-etal-2023-wspalign,
+    title = "{WSPA}lign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction",
+    author = "Wu, Qiyu  and Nagata, Masaaki  and Tsuruoka, Yoshimasa",
+    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
+    month = jul,
+    year = "2023",
+    address = "Toronto, Canada",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2023.acl-long.621",
+    pages = "11084--11099",
+}
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "qiyuw/WSPAlign-mbert-base",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6411f5d06f2fb5c743c1b0da8cdffa090bd2d1c1fbb51a04d16d8dae854cf20e
+size 1418231813

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:693bb1f981bcf53c6b2bc35a1956b7e9dbd3aecc1f95d7f1022ae4a7a7e0dbf2
+size 709129709

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631ea08acf301fa9ca40faaf4c9fa70ccacf5e60387a660ca000e7e7ad0bea66
+size 627

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "qiyuw/WSPAlign-mbert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf603ca54f0fa767e48fd6a738450ad333d423e2c24dda89d87f713b8318b9e
+size 1915