README.md
| 1 | --- |
| 2 | language: en |
| 3 | license: cc-by-4.0 |
| 4 | datasets: |
| 5 | - squad_v2 |
| 6 | model-index: |
| 7 | - name: deepset/bert-base-cased-squad2 |
| 8 | results: |
| 9 | - task: |
| 10 | type: question-answering |
| 11 | name: Question Answering |
| 12 | dataset: |
| 13 | name: squad_v2 |
| 14 | type: squad_v2 |
| 15 | config: squad_v2 |
| 16 | split: validation |
| 17 | metrics: |
| 18 | - type: exact_match |
| 19 | value: 71.1517 |
| 20 | name: Exact Match |
| 21 | verified: true |
| 22 | verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGZlNmQ1YzIzMWUzNTg4YmI4NWVhYThiMzE2ZGZmNWUzNDM3NWI0ZGJkNzliNGUxNTY2MDA5MWVkYjAwYWZiMCIsInZlcnNpb24iOjF9.iUvVdy5c4hoXkwlThJankQqG9QXzNilvfF1_4P0oL8X-jkY5Q6YSsZx6G6cpgXogqFpn7JlE_lP6_OT0VIamCg |
| 23 | - type: f1 |
| 24 | value: 74.6714 |
| 25 | name: F1 |
| 26 | verified: true |
| 27 | verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWE5OGNjODhmY2Y0NWIyZDIzMmQ2NmRjZGYyYTYzOWMxZDUzYzg4YjBhNTRiNTY4NTc0M2IxNjI5NWI5ZDM0NCIsInZlcnNpb24iOjF9.IqU9rbzUcKmDEoLkwCUZTKSH0ZFhtqgnhOaEDKKnaRMGBJLj98D5V4VirYT6jLh8FlR0FiwvMTMjReBcfTisAQ |
| 28 | --- |
| 29 | |
| 30 | This is a BERT base cased model trained on SQuAD v2 |
| 31 | |
| 32 | ## Overview |
| 33 | **Language model:** bert-base-cased |
| 34 | **Language:** English |
| 35 | **Downstream-task:** Extractive QA |
| 36 | **Training data:** SQuAD 2.0 |
| 37 | **Eval data:** SQuAD 2.0 |
| 38 | **Code:** See [an example extractive QA pipeline built with Haystack](https://haystack.deepset.ai/tutorials/34_extractive_qa_pipeline) |
| 39 | |
| 40 | ## Usage |
| 41 | |
| 42 | ### In Haystack |
| 43 | Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. |
| 44 | To load and run the model with [Haystack](https://github.com/deepset-ai/haystack/): |
| 45 | ```python |
| 46 | # After running pip install haystack-ai "transformers[torch,sentencepiece]" |
| 47 | |
| 48 | from haystack import Document |
| 49 | from haystack.components.readers import ExtractiveReader |
| 50 | |
| 51 | docs = [ |
| 52 | Document(content="Python is a popular programming language"), |
| 53 | Document(content="python ist eine beliebte Programmiersprache"), |
| 54 | ] |
| 55 | |
| 56 | reader = ExtractiveReader(model="deepset/bert-base-cased-squad2") |
| 57 | reader.warm_up() |
| 58 | |
| 59 | question = "What is a popular programming language?" |
| 60 | result = reader.run(query=question, documents=docs) |
| 61 | # {'answers': [ExtractedAnswer(query='What is a popular programming language?', score=0.5740374326705933, data='python', document=Document(id=..., content: '...'), context=None, document_offset=ExtractedAnswer.Span(start=0, end=6),...)]} |
| 62 | ``` |
| 63 | For a complete example with an extractive question answering pipeline that scales over many documents, check out the [corresponding Haystack tutorial](https://haystack.deepset.ai/tutorials/34_extractive_qa_pipeline). |
| 64 | |
| 65 | ### In Transformers |
| 66 | ```python |
| 67 | from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline |
| 68 | |
| 69 | model_name = "deepset/bert-base-cased-squad2" |
| 70 | |
| 71 | # a) Get predictions |
| 72 | nlp = pipeline('question-answering', model=model_name, tokenizer=model_name) |
| 73 | QA_input = { |
| 74 | 'question': 'Why is model conversion important?', |
| 75 | 'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.' |
| 76 | } |
| 77 | res = nlp(QA_input) |
| 78 | |
| 79 | # b) Load model & tokenizer |
| 80 | model = AutoModelForQuestionAnswering.from_pretrained(model_name) |
| 81 | tokenizer = AutoTokenizer.from_pretrained(model_name) |
| 82 | ``` |
| 83 | |
| 84 | ## About us |
| 85 | |
| 86 | <div class="grid lg:grid-cols-2 gap-x-4 gap-y-3"> |
| 87 | <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> |
| 88 | <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/> |
| 89 | </div> |
| 90 | <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> |
| 91 | <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/> |
| 92 | </div> |
| 93 | </div> |
| 94 | |
| 95 | [deepset](http://deepset.ai/) is the company behind the production-ready open-source AI framework [Haystack](https://haystack.deepset.ai/). |
| 96 | |
| 97 | Some of our other work: |
| 98 | - [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")](https://huggingface.co/deepset/tinyroberta-squad2) |
| 99 | - [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert) |
| 100 | - [GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")](https://deepset.ai/germanquad) |
| 101 | |
| 102 | ## Get in touch and join the Haystack community |
| 103 | |
| 104 | <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://docs.haystack.deepset.ai">Documentation</a></strong>. |
| 105 | |
| 106 | We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p> |
| 107 | |
| 108 | [Twitter](https://twitter.com/Haystack_AI) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://haystack.deepset.ai/) | [YouTube](https://www.youtube.com/@deepset_ai) |
| 109 | |
| 110 | By the way: [we're hiring!](http://www.deepset.ai/jobs) |