julianrisch commited on
Commit
eea39c6
1 Parent(s): ec78f8d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -18
README.md CHANGED
@@ -140,7 +140,7 @@ model-index:
140
  name: F1
141
  ---
142
 
143
- # deberta-v3-base for QA
144
 
145
  This is the [deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-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.
146
 
@@ -151,7 +151,7 @@ This is the [deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base)
151
  **Downstream-task:** Extractive QA
152
  **Training data:** SQuAD 2.0
153
  **Eval data:** SQuAD 2.0
154
- **Code:** See [an example QA pipeline on Haystack](https://haystack.deepset.ai/tutorials/first-qa-system)
155
  **Infrastructure**: 1x NVIDIA A10G
156
 
157
  ## Hyperparameters
@@ -171,17 +171,34 @@ max_query_length = 64
171
  ## Usage
172
 
173
  ### In Haystack
174
- 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/):
 
175
  ```python
176
- reader = FARMReader(model_name_or_path="deepset/deberta-v3-base-squad2")
177
- # or
178
- reader = TransformersReader(model_name_or_path="deepset/deberta-v3-base-squad2",tokenizer="deepset/deberta-v3-base-squad2")
 
 
 
 
 
 
 
 
 
 
 
 
 
179
  ```
 
180
 
181
  ### In Transformers
182
  ```python
183
  from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
184
- model_name = "deepset/deberta-v3-base-squad2"
 
 
185
  # a) Get predictions
186
  nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
187
  QA_input = {
@@ -189,38 +206,42 @@ QA_input = {
189
  'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
190
  }
191
  res = nlp(QA_input)
 
192
  # b) Load model & tokenizer
193
  model = AutoModelForQuestionAnswering.from_pretrained(model_name)
194
  tokenizer = AutoTokenizer.from_pretrained(model_name)
195
  ```
196
 
 
197
  ## Authors
198
  **Sebastian Lee:** sebastian.lee [at] deepset.ai
199
  **Timo Möller:** timo.moeller [at] deepset.ai
200
  **Malte Pietsch:** malte.pietsch [at] deepset.ai
201
 
202
  ## About us
 
203
  <div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
204
  <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
205
- <img alt="" src="https://huggingface.co/spaces/deepset/README/resolve/main/haystack-logo-colored.svg" class="w-40"/>
206
  </div>
207
- <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
208
- <img alt="" src="https://huggingface.co/spaces/deepset/README/resolve/main/deepset-logo-colored.svg" class="w-40"/>
209
  </div>
210
  </div>
211
 
212
- [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.
213
-
214
 
215
  Some of our other work:
216
- - [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")]([https://huggingface.co/deepset/tinyroberta-squad2)
217
- - [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
218
- - [GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")](https://deepset.ai/germanquad)
219
 
220
  ## Get in touch and join the Haystack community
221
 
222
- <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>.
 
 
223
 
224
- We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community/join">Discord community open to everyone!</a></strong></p>
225
 
226
- [Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community/join) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://deepset.ai)
 
140
  name: F1
141
  ---
142
 
143
+ # deberta-v3-base for Extractive QA
144
 
145
  This is the [deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-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.
146
 
 
151
  **Downstream-task:** Extractive QA
152
  **Training data:** SQuAD 2.0
153
  **Eval data:** SQuAD 2.0
154
+ **Code:** See [an example extractive QA pipeline built with Haystack](https://haystack.deepset.ai/tutorials/34_extractive_qa_pipeline)
155
  **Infrastructure**: 1x NVIDIA A10G
156
 
157
  ## Hyperparameters
 
171
  ## Usage
172
 
173
  ### In Haystack
174
+ 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.
175
+ To load and run the model with [Haystack](https://github.com/deepset-ai/haystack/):
176
  ```python
177
+ # After running pip install haystack-ai "transformers[torch,sentencepiece]"
178
+
179
+ from haystack import Document
180
+ from haystack.components.readers import ExtractiveReader
181
+
182
+ docs = [
183
+ Document(content="Python is a popular programming language"),
184
+ Document(content="python ist eine beliebte Programmiersprache"),
185
+ ]
186
+
187
+ reader = ExtractiveReader(model="deepset/roberta-base-squad2")
188
+ reader.warm_up()
189
+
190
+ question = "What is a popular programming language?"
191
+ result = reader.run(query=question, documents=docs)
192
+ # {'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),...)]}
193
  ```
194
+ 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).
195
 
196
  ### In Transformers
197
  ```python
198
  from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
199
+
200
+ model_name = "deepset/roberta-base-squad2"
201
+
202
  # a) Get predictions
203
  nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
204
  QA_input = {
 
206
  'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
207
  }
208
  res = nlp(QA_input)
209
+
210
  # b) Load model & tokenizer
211
  model = AutoModelForQuestionAnswering.from_pretrained(model_name)
212
  tokenizer = AutoTokenizer.from_pretrained(model_name)
213
  ```
214
 
215
+
216
  ## Authors
217
  **Sebastian Lee:** sebastian.lee [at] deepset.ai
218
  **Timo Möller:** timo.moeller [at] deepset.ai
219
  **Malte Pietsch:** malte.pietsch [at] deepset.ai
220
 
221
  ## About us
222
+
223
  <div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
224
  <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
225
+ <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/>
226
  </div>
227
+ <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
228
+ <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/>
229
  </div>
230
  </div>
231
 
232
+ [deepset](http://deepset.ai/) is the company behind the production-ready open-source AI framework [Haystack](https://haystack.deepset.ai/).
 
233
 
234
  Some of our other work:
235
+ - [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")](https://huggingface.co/deepset/tinyroberta-squad2)
236
+ - [German BERT](https://deepset.ai/german-bert), [GermanQuAD and GermanDPR](https://deepset.ai/germanquad), [German embedding model](https://huggingface.co/mixedbread-ai/deepset-mxbai-embed-de-large-v1)
237
+ - [deepset Cloud](https://www.deepset.ai/deepset-cloud-product), [deepset Studio](https://www.deepset.ai/deepset-studio)
238
 
239
  ## Get in touch and join the Haystack community
240
 
241
+ <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>.
242
+
243
+ We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p>
244
 
245
+ [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)
246
 
247
+ By the way: [we're hiring!](http://www.deepset.ai/jobs)