lewtun
HF staff
commited on
Commit
f8841e3
1 Parent(s): 20a729d
README.md CHANGED
@@ -1,3 +1,117 @@
1
  ---
2
- license: apache-2.0
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language: en
3
+ datasets:
4
+ - squad_v2
5
+ license: cc-by-4.0
6
  ---
7
+
8
+ # roberta-base for QA
9
+
10
+ This is the [roberta-base](https://huggingface.co/roberta-base) model, fine-tuned using the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.
11
+
12
+
13
+ ## Overview
14
+ **Language model:** roberta-base
15
+ **Language:** English
16
+ **Downstream-task:** Extractive QA
17
+ **Training data:** SQuAD 2.0
18
+ **Eval data:** SQuAD 2.0
19
+ **Code:** See [an example QA pipeline on Haystack](https://haystack.deepset.ai/tutorials/first-qa-system)
20
+ **Infrastructure**: 4x Tesla v100
21
+
22
+ ## Hyperparameters
23
+
24
+ ```
25
+ batch_size = 96
26
+ n_epochs = 2
27
+ base_LM_model = "roberta-base"
28
+ max_seq_len = 386
29
+ learning_rate = 3e-5
30
+ lr_schedule = LinearWarmup
31
+ warmup_proportion = 0.2
32
+ doc_stride=128
33
+ max_query_length=64
34
+ ```
35
+
36
+ ## Using a distilled model instead
37
+ Please note that we have also released a distilled version of this model called [deepset/tinyroberta-squad2](https://huggingface.co/deepset/tinyroberta-squad2). The distilled model has a comparable prediction quality and runs at twice the speed of the base model.
38
+
39
+ ## Usage
40
+
41
+ ### In Haystack
42
+ Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in [Haystack](https://github.com/deepset-ai/haystack/):
43
+ ```python
44
+ reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2")
45
+ # or
46
+ reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")
47
+ ```
48
+ For a complete example of ``roberta-base-squad2`` being used for Question Answering, check out the [Tutorials in Haystack Documentation](https://haystack.deepset.ai/tutorials/first-qa-system)
49
+
50
+ ### In Transformers
51
+ ```python
52
+ from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
53
+
54
+ model_name = "deepset/roberta-base-squad2"
55
+
56
+ # a) Get predictions
57
+ nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
58
+ QA_input = {
59
+ 'question': 'Why is model conversion important?',
60
+ 'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
61
+ }
62
+ res = nlp(QA_input)
63
+
64
+ # b) Load model & tokenizer
65
+ model = AutoModelForQuestionAnswering.from_pretrained(model_name)
66
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
67
+ ```
68
+
69
+ ## Performance
70
+ Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
71
+
72
+ ```
73
+ "exact": 79.87029394424324,
74
+ "f1": 82.91251169582613,
75
+
76
+ "total": 11873,
77
+ "HasAns_exact": 77.93522267206478,
78
+ "HasAns_f1": 84.02838248389763,
79
+ "HasAns_total": 5928,
80
+ "NoAns_exact": 81.79983179142137,
81
+ "NoAns_f1": 81.79983179142137,
82
+ "NoAns_total": 5945
83
+ ```
84
+
85
+ ## Authors
86
+ **Branden Chan:** branden.chan@deepset.ai
87
+ **Timo Möller:** timo.moeller@deepset.ai
88
+ **Malte Pietsch:** malte.pietsch@deepset.ai
89
+ **Tanay Soni:** tanay.soni@deepset.ai
90
+
91
+ ## About us
92
+ <div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
93
+ <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
94
+ <img alt="" src="https://huggingface.co/spaces/deepset/README/resolve/main/haystack-logo-colored.svg" class="w-40"/>
95
+ </div>
96
+ <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
97
+ <img alt="" src="https://huggingface.co/spaces/deepset/README/resolve/main/deepset-logo-colored.svg" class="w-40"/>
98
+ </div>
99
+ </div>
100
+
101
+ [deepset](http://deepset.ai/) is the company behind the open-source NLP framework [Haystack](https://haystack.deepset.ai/) which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc.
102
+
103
+
104
+ Some of our other work:
105
+ - [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")]([https://huggingface.co/deepset/tinyroberta-squad2)
106
+ - [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
107
+ - [GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")](https://deepset.ai/germanquad)
108
+
109
+ ## Get in touch and join the Haystack community
110
+
111
+ <p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://haystack.deepset.ai">Documentation</a></strong>.
112
+
113
+ We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community/join"><img alt="slack" class="h-7 inline-block m-0" style="margin: 0" src="https://huggingface.co/spaces/deepset/README/resolve/main/Slack_RGB.png"/>community open to everyone!</a></strong></p>
114
+
115
+ [Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Slack](https://haystack.deepset.ai/community/join) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://deepset.ai)
116
+
117
+ By the way: [we're hiring!](http://www.deepset.ai/jobs)
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForQuestionAnswering"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "language": "english",
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "name": "Roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "type_vocab_size": 1,
23
+ "vocab_size": 50265
24
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8d759d881d9c1b39dbf4ee451fb8a8c2d43ccbd180218863a54ffd9b4d2447
3
+ size 496233457
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b64ccefc1bcb569b604baea27eb873e5482fdf6eb3ceff1fb5368397db5aed
3
+ size 496313727
rust_model.ot ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a16ed126bbc8c4cf794406bac0c7946f62d0f175c02dc54d77a00a6255597ed
3
+ size 498638704
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
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}}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b672dd16f09f6f805d407800278e60217b9d7c040df1dde5098765a40cdc88a
3
+ size 496513256
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null}
vocab.json ADDED
The diff for this file is too large to render. See raw diff