Add model files

README.md

@@ -0,0 +1,19 @@
+---
+language: en
+tags:
+- tapas
+license: apache-2.0
+---
+
+This model contains the converted PyTorch checkpoint of the original Tensorflow model available in the [TaPas repository](https://github.com/google-research/tapas/blob/master/DENSE_TABLE_RETRIEVER.md#reader-models).
+It is described in Herzig et al.'s (2021) [paper](https://aclanthology.org/2021.naacl-main.43/) _Open Domain Question Answering over Tables via Dense Retrieval_.
+
+
+# Usage
+## In Haystack
+If you want to use this model for question-answering over tables, you can load it in [Haystack](https://github.com/deepset-ai/haystack/):
+```python
+from haystack.nodes import TableReader
+
+table_reader = TableReader(model_name_or_path="deepset/tapas-large-nq-hn-reader")
+```

config.json

@@ -0,0 +1,62 @@
+{
+  "aggregation_labels": null,
+  "aggregation_loss_weight": 1.0,
+  "aggregation_temperature": 1.0,
+  "allow_empty_column_selection": false,
+  "answer_loss_cutoff": null,
+  "answer_loss_importance": 1.0,
+  "architectures": [
+    "TapasForScoredQA"
+  ],
+  "attention_probs_dropout_prob": 0.034,
+  "average_approximation_function": "ratio",
+  "average_logits_per_cell": false,
+  "cell_selection_preference": null,
+  "disable_per_token_loss": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 1024,
+  "huber_loss_delta": null,
+  "init_cell_selection_weights_to_zero": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_num_columns": 32,
+  "max_num_rows": 64,
+  "max_position_embeddings": 1024,
+  "model_type": "tapas",
+  "no_aggregation_label_index": null,
+  "num_aggregation_labels": 0,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "positive_label_weight": 10.0,
+  "reset_position_index_per_cell": true,
+  "select_one_column": true,
+  "softmax_temperature": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "type_vocab_size": [
+    3,
+    256,
+    256,
+    2,
+    256,
+    256,
+    10
+  ],
+  "type_vocab_sizes": [
+    3,
+    256,
+    256,
+    2,
+    256,
+    256,
+    10
+  ],
+  "use_answer_as_supervision": null,
+  "use_gumbel_for_aggregation": false,
+  "use_gumbel_for_cells": false,
+  "use_normalized_answer_loss": false,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9b7c65217e5100933fc3f740ca4299517aca14a6f64d2b58e34f5f8be0e64c
+size 1347084063

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "empty_token": "[EMPTY]", "tokenize_chinese_chars": true, "strip_accents": null, "cell_trim_length": -1, "max_column_id": null, "max_row_id": null, "strip_column_names": false, "update_answer_coordinates": false, "min_question_length": null, "max_question_length": null, "model_max_length": 512, "additional_special_tokens": ["[EMPTY]"], "tokenizer_class": "TapasTokenizer"}