+{"cells":[{"cell_type":"markdown","source":["#### Transformers Example\n\nhttps://huggingface.co/facebook/bart-large-cnn"],"metadata":{"application/vnd.databricks.v1+cell":{"showTitle":false,"cellMetadata":{},"nuid":"4af7312e-0bc2-4a47-9fed-aec2caf2d781","inputWidgets":{},"title":""}}},{"cell_type":"code","source":["!pip install transformers"],"metadata":{"application/vnd.databricks.v1+cell":{"showTitle":false,"cellMetadata":{},"nuid":"d990cbc3-9f03-4322-a406-945c427d7890","inputWidgets":{},"title":""}},"outputs":[{"output_type":"display_data","metadata":{"application/vnd.databricks.v1+output":{"datasetInfos":[],"data":"Looking in indexes: https://artifacts.rbi.tech/artifactory/api/pypi/pypi-org-pypi-proxy/simple/\r\nRequirement already satisfied: transformers in /databricks/python3/lib/python3.9/site-packages (4.20.0)\r\nRequirement already satisfied: packaging>=20.0 in /databricks/python3/lib/python3.9/site-packages (from transformers) (21.0)\r\nRequirement already satisfied: pyyaml>=5.1 in /local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages (from transformers) (5.4.1)\r\nRequirement already satisfied: filelock in /databricks/python3/lib/python3.9/site-packages (from transformers) (3.3.1)\r\nRequirement already satisfied: numpy>=1.17 in /databricks/python3/lib/python3.9/site-packages (from transformers) (1.20.3)\r\nRequirement already satisfied: regex!=2019.12.17 in /databricks/python3/lib/python3.9/site-packages (from transformers) (2021.8.3)\r\nRequirement already satisfied: tokenizers!=0.11.3,<0.13,>=0.11.1 in /databricks/python3/lib/python3.9/site-packages (from transformers) (0.12.1)\r\nRequirement already satisfied: tqdm>=4.27 in /databricks/python3/lib/python3.9/site-packages (from transformers) (4.62.3)\r\nRequirement already satisfied: huggingface-hub<1.0,>=0.1.0 in /databricks/python3/lib/python3.9/site-packages (from transformers) (0.8.1)\r\nRequirement already satisfied: requests in /databricks/python3/lib/python3.9/site-packages (from transformers) (2.26.0)\r\nRequirement already satisfied: typing-extensions>=3.7.4.3 in /databricks/python3/lib/python3.9/site-packages (from huggingface-hub<1.0,>=0.1.0->transformers) (3.10.0.2)\r\nRequirement already satisfied: pyparsing>=2.0.2 in /databricks/python3/lib/python3.9/site-packages (from packaging>=20.0->transformers) (3.0.4)\r\nRequirement already satisfied: idna<4,>=2.5 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (3.2)\r\nRequirement already satisfied: charset-normalizer~=2.0.0 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (2.0.4)\r\nRequirement already satisfied: urllib3<1.27,>=1.21.1 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (1.26.7)\r\nRequirement already satisfied: certifi>=2017.4.17 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (2021.10.8)\r\n","removedWidgets":[],"addedWidgets":{},"metadata":{},"type":"ansi","arguments":{}}},"output_type":"display_data","data":{"text/plain":["Looking in indexes: https://artifacts.rbi.tech/artifactory/api/pypi/pypi-org-pypi-proxy/simple/\r\nRequirement already satisfied: transformers in /databricks/python3/lib/python3.9/site-packages (4.20.0)\r\nRequirement already satisfied: packaging>=20.0 in /databricks/python3/lib/python3.9/site-packages (from transformers) (21.0)\r\nRequirement already satisfied: pyyaml>=5.1 in /local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages (from transformers) (5.4.1)\r\nRequirement already satisfied: filelock in /databricks/python3/lib/python3.9/site-packages (from transformers) (3.3.1)\r\nRequirement already satisfied: numpy>=1.17 in /databricks/python3/lib/python3.9/site-packages (from transformers) (1.20.3)\r\nRequirement already satisfied: regex!=2019.12.17 in /databricks/python3/lib/python3.9/site-packages (from transformers) (2021.8.3)\r\nRequirement already satisfied: tokenizers!=0.11.3,<0.13,>=0.11.1 in /databricks/python3/lib/python3.9/site-packages (from transformers) (0.12.1)\r\nRequirement already satisfied: tqdm>=4.27 in /databricks/python3/lib/python3.9/site-packages (from transformers) (4.62.3)\r\nRequirement already satisfied: huggingface-hub<1.0,>=0.1.0 in /databricks/python3/lib/python3.9/site-packages (from transformers) (0.8.1)\r\nRequirement already satisfied: requests in /databricks/python3/lib/python3.9/site-packages (from transformers) (2.26.0)\r\nRequirement already satisfied: typing-extensions>=3.7.4.3 in /databricks/python3/lib/python3.9/site-packages (from huggingface-hub<1.0,>=0.1.0->transformers) (3.10.0.2)\r\nRequirement already satisfied: pyparsing>=2.0.2 in /databricks/python3/lib/python3.9/site-packages (from packaging>=20.0->transformers) (3.0.4)\r\nRequirement already satisfied: idna<4,>=2.5 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (3.2)\r\nRequirement already satisfied: charset-normalizer~=2.0.0 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (2.0.4)\r\nRequirement already satisfied: urllib3<1.27,>=1.21.1 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (1.26.7)\r\nRequirement already satisfied: certifi>=2017.4.17 in /databricks/python3/lib/python3.9/site-packages (from requests->transformers) (2021.10.8)\r\n"]}}],"execution_count":0},{"cell_type":"code","source":["from transformers import pipeline"],"metadata":{"application/vnd.databricks.v1+cell":{"showTitle":false,"cellMetadata":{},"nuid":"9fa5b327-dbc6-4862-b808-e7223757b3bf","inputWidgets":{},"title":""}},"outputs":[],"execution_count":0},{"cell_type":"code","source":["summarizer = pipeline(\"summarization\", model=\"facebook/bart-large-cnn\")"],"metadata":{"application/vnd.databricks.v1+cell":{"showTitle":false,"cellMetadata":{},"nuid":"a18146d8-0d05-462a-bff5-9de4eea13fd1","inputWidgets":{},"title":""}},"outputs":[],"execution_count":0},{"cell_type":"code","source":["ARTICLE = \"\"\" \nHow much money does Trump have?\nA lot. Trump’s political operation, led by his leadership PAC Save America, is sitting on more than $100 million, according to the most recent filings with federal regulators.\n\nSave America has been at the heart of Trump’s post-presidential fundraising. Leadership PACs are generally established as a way to allow political figures to support other candidates. But they also serve as campaigns-in-waiting for presidential contenders – funding travel and polling and paying the staff members who ultimately join a White House campaign.\n\nLeadership PACs also can underwrite personal expenses.\n\nSave America, for instance, has spent more than $8.5 million on legal expenses since the start of 2021 – with some of it going to firms defending Trump in personal legal matters, such as the sweeping lawsuit that New York Attorney General Letitia James brought in September, alleging fraud in the Trump Organization’s business practices. Trump has denied wrongdoing.\n\nThe former president’s close allies also recently established a super PAC, which can raise and spend unlimited sums but is barred from coordinating its activities with the candidates it supports.\n\nLast month, Save America transferred $20 million to the new Trump-aligned super PAC, MAGA Inc., with the goal of aiding Trump’s favored candidates in the midterms.\n\nPolitical observers say that transfer might foreshadow one way Save America’s big war chest could benefit Trump’s candidacy in the months ahead.\n\"\"\""],"metadata":{"application/vnd.databricks.v1+cell":{"showTitle":false,"cellMetadata":{},"nuid":"6c67428b-62b0-4c42-9822-eb2d3e99ff49","inputWidgets":{},"title":""}},"outputs":[],"execution_count":0},{"cell_type":"code","source":["print(summarizer(ARTICLE, max_length=500, min_length=30, do_sample=False))"],"metadata":{"application/vnd.databricks.v1+cell":{"showTitle":false,"cellMetadata":{},"nuid":"bd6712ba-a5d0-4031-91bd-f41cc5eecc94","inputWidgets":{},"title":""}},"outputs":[{"output_type":"display_data","metadata":{"application/vnd.databricks.v1+output":{"datasetInfos":[],"data":"Your max_length is set to 500, but you input_length is only 315. You might consider decreasing max_length manually, e.g. summarizer('...', max_length=157)\n[{'summary_text': \"Leadership PACs are generally established as a way to allow political figures to support other candidates. But they also serve as campaigns-in-waiting for presidential contenders. Trump's political operation, led by his leadership PAC Save America, is sitting on more than $100 million.\"}]\n","removedWidgets":[],"addedWidgets":{},"metadata":{},"type":"ansi","arguments":{}}},"output_type":"display_data","data":{"text/plain":["Your max_length is set to 500, but you input_length is only 315. You might consider decreasing max_length manually, e.g. summarizer('...', max_length=157)\n[{'summary_text': \"Leadership PACs are generally established as a way to allow political figures to support other candidates. But they also serve as campaigns-in-waiting for presidential contenders. Trump's political operation, led by his leadership PAC Save America, is sitting on more than $100 million.\"}]\n"]}}],"execution_count":0},{"cell_type":"code","source":[""],"metadata":{"application/vnd.databricks.v1+cell":{"showTitle":false,"cellMetadata":{},"nuid":"94d48aba-c0d8-43be-954d-ae9c24dfbb3b","inputWidgets":{},"title":""}},"outputs":[],"execution_count":0}],"metadata":{"application/vnd.databricks.v1+notebook":{"notebookName":"07_NLP_Transformers","dashboards":[],"notebookMetadata":{"pythonIndentUnit":4},"language":"python","widgets":{},"notebookOrigID":3150076713424332}},"nbformat":4,"nbformat_minor":0}
0 commit comments