Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
 ---
-license: mit
+language: en
+tags:
+- table-fact-checking
+datasets:
+- tabfact
 ---
+
+# ReasTAP
+
+ReasTAP is a table reasoning model proposed in the EMNLP 2022 paper [ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples](https://arxiv.org/pdf/2210.12374.pdf). The original Github repository is [https://github.com/Yale-LILY/ReasTAP](https://github.com/Yale-LILY/ReasTAP).
+
+## Description
+
+`Yale-LILY/reastap-large-finetuned-tabfact` is initialized with `Yale-LILY/reastap-large` and finetuned on [TabFact](https://huggingface.co/datasets/tab_fact).
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import pandas as pd
+
+tokenizer = AutoTokenizer.from_pretrained("Yale-LILY/reastap-large-finetuned-tabfact")
+model = AutoModelForSequenceClassification.from_pretrained("Yale-LILY/reastap-large-finetuned-tabfact")
+
+data = {
+    "year": [1896, 1900, 1904, 2004, 2008, 2012],
+    "city": ["athens", "paris", "st. louis", "athens", "beijing", "london"]
+}
+table = pd.DataFrame.from_dict(data)
+
+query = "beijing hosts the olympic games in 2012"
+encoding = tokenizer(table=table, query=query, return_tensors="pt")
+
+outputs = model(**encoding)
+output_id = int(outputs.logits[0].argmax(dim=0))
+print(model.config.id2label[output_id])
+```
+
+## Reference
+
+```bibtex
+@inproceedings{zhao-etal-2022-reastap,
+    title = "{R}eas{TAP}: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples",
+    author = "Zhao, Yilun  and
+      Nan, Linyong  and
+      Qi, Zhenting  and
+      Zhang, Rui  and
+      Radev, Dragomir",
+    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
+    month = dec,
+    year = "2022",
+    address = "Abu Dhabi, United Arab Emirates",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2022.emnlp-main.615",
+    pages = "9006--9018",
+    abstract = "Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding table structures, but they still struggle with tasks that require various table reasoning skills. In this work, we develop ReasTAP to show that high-level table reasoning skills can be injected into models during pre-training without a complex table-specific architecture design. We define 7 table reasoning skills, such as numerical operation, temporal comparison, and conjunction. Each reasoning skill is associated with one example generator, which synthesizes questions over semi-structured tables according to the sampled templates. We model the table pre-training task as a sequence generation task and pre-train ReasTAP to generate precise answers of the synthetic examples. ReasTAP is evaluated on four benchmarks covering three downstream tasks including 1) WikiSQL-Weak and WikiTQ for Table Question Answering, 2) TabFact for Table Fact Verification, and 3) LogicNLG for Faithful Table-to-Text Generation. Experimental results demonstrate that ReasTAP achieves new state-of-the-art results on all of them and delivers a significant improvement under low-resource setting. Our code is publicly available at https://github.com/Yale-LILY/ReasTAP.",
+}
+```

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "Yale-LILY/reastap-large-finetuned-tabfact",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "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,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "Refused",
+    "1": "Entailed"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Entailed": 1,
+    "Refused": 0
+  },
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede9186e8b205bc6a7ed286a80e0c3bc804669c6b57a3974a7fc21c0053234ab
+size 1629547865

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_cell_length": 15,
+  "model_max_length": 1024,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "TapexTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": true
+}