Zhengbao Jiang commited on
Commit
7a9b0d0
1 Parent(s): cd0ae24

init commit

Browse files
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - question-answering
5
+ ---
6
+
7
+ # ReAtt
8
+ 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).
9
+
10
+ ## Description
11
+ `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.
12
+
13
+ ## Usage
14
+ Please refer to [https://github.com/jzbjyb/ReAtt](https://github.com/jzbjyb/ReAtt) for instructions to use this model.
15
+
16
+ ## Reference
17
+
18
+ ```bibtex
19
+ @inproceedings{jiang-etal-2022-reatt,
20
+ title = {Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer},
21
+ author = {Zhengbao Jiang and Luyu Gao and Jun Araki and Haibo Ding and Zhiruo Wang and Jamie Callan and Graham Neubig},
22
+ booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},
23
+ address = {Abu Dhabi, UAE},
24
+ month = {December},
25
+ year = {2022}
26
+ }
27
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neulab/reatt-large-nq-bioasq",
3
+ "architectures": [
4
+ "ReAttForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "num_decoder_layers": 24,
18
+ "num_heads": 16,
19
+ "num_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.15.0",
26
+ "use_cache": true,
27
+ "vocab_size": 32128,
28
+ "retrieval_layer": 12,
29
+ "retrieval_head": 6,
30
+ "distillation_tau": 0.001
31
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df3a276f643695c735fc7682352f23f43c09a694688db013c78648c18be2bd3
3
+ size 3132795021
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "unk_token": "<unk>",
4
+ "pad_token": "<pad>",
5
+ "extra_ids": 100,
6
+ "additional_special_tokens": [
7
+ "<extra_id_0>",
8
+ "<extra_id_1>",
9
+ "<extra_id_2>",
10
+ "<extra_id_3>",
11
+ "<extra_id_4>",
12
+ "<extra_id_5>",
13
+ "<extra_id_6>",
14
+ "<extra_id_7>",
15
+ "<extra_id_8>",
16
+ "<extra_id_9>",
17
+ "<extra_id_10>",
18
+ "<extra_id_11>",
19
+ "<extra_id_12>",
20
+ "<extra_id_13>",
21
+ "<extra_id_14>",
22
+ "<extra_id_15>",
23
+ "<extra_id_16>",
24
+ "<extra_id_17>",
25
+ "<extra_id_18>",
26
+ "<extra_id_19>",
27
+ "<extra_id_20>",
28
+ "<extra_id_21>",
29
+ "<extra_id_22>",
30
+ "<extra_id_23>",
31
+ "<extra_id_24>",
32
+ "<extra_id_25>",
33
+ "<extra_id_26>",
34
+ "<extra_id_27>",
35
+ "<extra_id_28>",
36
+ "<extra_id_29>",
37
+ "<extra_id_30>",
38
+ "<extra_id_31>",
39
+ "<extra_id_32>",
40
+ "<extra_id_33>",
41
+ "<extra_id_34>",
42
+ "<extra_id_35>",
43
+ "<extra_id_36>",
44
+ "<extra_id_37>",
45
+ "<extra_id_38>",
46
+ "<extra_id_39>",
47
+ "<extra_id_40>",
48
+ "<extra_id_41>",
49
+ "<extra_id_42>",
50
+ "<extra_id_43>",
51
+ "<extra_id_44>",
52
+ "<extra_id_45>",
53
+ "<extra_id_46>",
54
+ "<extra_id_47>",
55
+ "<extra_id_48>",
56
+ "<extra_id_49>",
57
+ "<extra_id_50>",
58
+ "<extra_id_51>",
59
+ "<extra_id_52>",
60
+ "<extra_id_53>",
61
+ "<extra_id_54>",
62
+ "<extra_id_55>",
63
+ "<extra_id_56>",
64
+ "<extra_id_57>",
65
+ "<extra_id_58>",
66
+ "<extra_id_59>",
67
+ "<extra_id_60>",
68
+ "<extra_id_61>",
69
+ "<extra_id_62>",
70
+ "<extra_id_63>",
71
+ "<extra_id_64>",
72
+ "<extra_id_65>",
73
+ "<extra_id_66>",
74
+ "<extra_id_67>",
75
+ "<extra_id_68>",
76
+ "<extra_id_69>",
77
+ "<extra_id_70>",
78
+ "<extra_id_71>",
79
+ "<extra_id_72>",
80
+ "<extra_id_73>",
81
+ "<extra_id_74>",
82
+ "<extra_id_75>",
83
+ "<extra_id_76>",
84
+ "<extra_id_77>",
85
+ "<extra_id_78>",
86
+ "<extra_id_79>",
87
+ "<extra_id_80>",
88
+ "<extra_id_81>",
89
+ "<extra_id_82>",
90
+ "<extra_id_83>",
91
+ "<extra_id_84>",
92
+ "<extra_id_85>",
93
+ "<extra_id_86>",
94
+ "<extra_id_87>",
95
+ "<extra_id_88>",
96
+ "<extra_id_89>",
97
+ "<extra_id_90>",
98
+ "<extra_id_91>",
99
+ "<extra_id_92>",
100
+ "<extra_id_93>",
101
+ "<extra_id_94>",
102
+ "<extra_id_95>",
103
+ "<extra_id_96>",
104
+ "<extra_id_97>",
105
+ "<extra_id_98>",
106
+ "<extra_id_99>"
107
+ ],
108
+ "sp_model_kwargs": {},
109
+ "model_max_length": 512,
110
+ "name_or_path": "neulab/reatt-large-nq-bioasq",
111
+ "special_tokens_map_file": null,
112
+ "tokenizer_class": "T5Tokenizer"
113
+ }