init commit

README.md

@@ -0,0 +1,27 @@
+---
+language: en
+tags:
+- question-answering
+---
+
+# ReAtt
+ReAtt is a retrieval-augmented model for knowledge-intensive tasks proposed in [Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer](https://arxiv.org/pdf/2212.02027.pdf). The original Github repository is [https://github.com/jzbjyb/ReAtt](https://github.com/jzbjyb/ReAtt).
+
+## Description
+`neulab/reatt-large-nq-bioasq` (based on T5 architecture) is initialized with `neulab/reatt-large-nq` and adapted on BioASQ dataset with end-to-end retrieval-augmented training.
+
+## Usage
+Please refer to [https://github.com/jzbjyb/ReAtt](https://github.com/jzbjyb/ReAtt) for instructions to use this model.
+
+## Reference
+
+```bibtex
+@inproceedings{jiang-etal-2022-reatt,
+    title = {Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer},
+    author = {Zhengbao Jiang and Luyu Gao and Jun Araki and Haibo Ding and Zhiruo Wang and Jamie Callan and Graham Neubig},
+    booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},
+    address = {Abu Dhabi, UAE},
+    month = {December},
+    year = {2022}
+}
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "neulab/reatt-large-nq-bioasq",
+  "architectures": [
+    "ReAttForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 32128,
+  "retrieval_layer": 12,
+  "retrieval_head": 6,
+  "distillation_tau": 0.001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df3a276f643695c735fc7682352f23f43c09a694688db013c78648c18be2bd3
+size 3132795021

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "pad_token": "<pad>",
+    "extra_ids": 100,
+    "additional_special_tokens": [
+        "<extra_id_0>",
+        "<extra_id_1>",
+        "<extra_id_2>",
+        "<extra_id_3>",
+        "<extra_id_4>",
+        "<extra_id_5>",
+        "<extra_id_6>",
+        "<extra_id_7>",
+        "<extra_id_8>",
+        "<extra_id_9>",
+        "<extra_id_10>",
+        "<extra_id_11>",
+        "<extra_id_12>",
+        "<extra_id_13>",
+        "<extra_id_14>",
+        "<extra_id_15>",
+        "<extra_id_16>",
+        "<extra_id_17>",
+        "<extra_id_18>",
+        "<extra_id_19>",
+        "<extra_id_20>",
+        "<extra_id_21>",
+        "<extra_id_22>",
+        "<extra_id_23>",
+        "<extra_id_24>",
+        "<extra_id_25>",
+        "<extra_id_26>",
+        "<extra_id_27>",
+        "<extra_id_28>",
+        "<extra_id_29>",
+        "<extra_id_30>",
+        "<extra_id_31>",
+        "<extra_id_32>",
+        "<extra_id_33>",
+        "<extra_id_34>",
+        "<extra_id_35>",
+        "<extra_id_36>",
+        "<extra_id_37>",
+        "<extra_id_38>",
+        "<extra_id_39>",
+        "<extra_id_40>",
+        "<extra_id_41>",
+        "<extra_id_42>",
+        "<extra_id_43>",
+        "<extra_id_44>",
+        "<extra_id_45>",
+        "<extra_id_46>",
+        "<extra_id_47>",
+        "<extra_id_48>",
+        "<extra_id_49>",
+        "<extra_id_50>",
+        "<extra_id_51>",
+        "<extra_id_52>",
+        "<extra_id_53>",
+        "<extra_id_54>",
+        "<extra_id_55>",
+        "<extra_id_56>",
+        "<extra_id_57>",
+        "<extra_id_58>",
+        "<extra_id_59>",
+        "<extra_id_60>",
+        "<extra_id_61>",
+        "<extra_id_62>",
+        "<extra_id_63>",
+        "<extra_id_64>",
+        "<extra_id_65>",
+        "<extra_id_66>",
+        "<extra_id_67>",
+        "<extra_id_68>",
+        "<extra_id_69>",
+        "<extra_id_70>",
+        "<extra_id_71>",
+        "<extra_id_72>",
+        "<extra_id_73>",
+        "<extra_id_74>",
+        "<extra_id_75>",
+        "<extra_id_76>",
+        "<extra_id_77>",
+        "<extra_id_78>",
+        "<extra_id_79>",
+        "<extra_id_80>",
+        "<extra_id_81>",
+        "<extra_id_82>",
+        "<extra_id_83>",
+        "<extra_id_84>",
+        "<extra_id_85>",
+        "<extra_id_86>",
+        "<extra_id_87>",
+        "<extra_id_88>",
+        "<extra_id_89>",
+        "<extra_id_90>",
+        "<extra_id_91>",
+        "<extra_id_92>",
+        "<extra_id_93>",
+        "<extra_id_94>",
+        "<extra_id_95>",
+        "<extra_id_96>",
+        "<extra_id_97>",
+        "<extra_id_98>",
+        "<extra_id_99>"
+    ],
+    "sp_model_kwargs": {},
+    "model_max_length": 512,
+    "name_or_path": "neulab/reatt-large-nq-bioasq",
+    "special_tokens_map_file": null,
+    "tokenizer_class": "T5Tokenizer"
+}