init commit

README.md

@@ -0,0 +1,52 @@
+---
+language: en
+tags:
+- tapex
+- table-question-answering
+datasets:
+- wikitablequestions
+---
+
+# OmniTab
+
+OmniTab is a table-based QA model proposed in [OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering](https://arxiv.org/pdf/2207.03637.pdf). The original Github repository is [https://github.com/jzbjyb/OmniTab](https://github.com/jzbjyb/OmniTab).
+
+## Description
+
+`neulab/omnitab-large-128shot` (based on BART architecture) is initialized with `microsoft/tapex-large` and continuously pretrained on natural and synthetic data (SQL2NL model trained in the 128-shot setting).
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import pandas as pd
+
+tokenizer = AutoTokenizer.from_pretrained("neulab/omnitab-large-128shot")
+model = AutoModelForSeq2SeqLM.from_pretrained("neulab/omnitab-large-128shot")
+
+data = {
+    "year": [1896, 1900, 1904, 2004, 2008, 2012],
+    "city": ["athens", "paris", "st. louis", "athens", "beijing", "london"]
+}
+table = pd.DataFrame.from_dict(data)
+
+query = "In which year did beijing host the Olympic Games?"
+encoding = tokenizer(table=table, query=query, return_tensors="pt")
+
+outputs = model.generate(**encoding)
+
+print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
+# [' 2008']
+```
+
+## Reference
+
+```bibtex
+@inproceedings{jiang-etal-2022-omnitab,
+  title = "{O}mni{T}ab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering",
+  author = "Jiang, Zhengbao and Mao, Yi and He, Pengcheng and Neubig, Graham and Chen, Weizhu",
+  booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
+  month = jul,
+  year = "2022",
+}
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "neulab/omnitab-large-128shot",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265,
+  "no_repeat_ngram_size": 3
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50dfb30432e7b1e1b7245e0e14c3bccd31ef5bc12387ab433d7ea5ca23fee025
+size 812847041

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+    "do_lower_case": false,
+    "errors": "replace",
+    "bos_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "eos_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "unk_token": {
+        "content": "<unk>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "sep_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "cls_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "pad_token": {
+        "content": "<pad>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "mask_token": {
+        "content": "<mask>",
+        "single_word": false,
+        "lstrip": true,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "add_prefix_space": false,
+    "max_cell_length": 15,
+    "model_max_length": 1024,
+    "special_tokens_map_file": null,
+    "name_or_path": "neulab/omnitab-large-128shot",
+    "use_fast": true,
+    "tokenizer_class": "TapexTokenizer"
+}