{"id":13534921,"url":"https://github.com/dmlc/gluon-nlp","last_synced_at":"2025-09-27T10:31:57.951Z","repository":{"id":38814282,"uuid":"128121076","full_name":"dmlc/gluon-nlp","owner":"dmlc","description":"NLP made easy","archived":true,"fork":false,"pushed_at":"2023-10-06T04:01:21.000Z","size":11414,"stargazers_count":2552,"open_issues_count":272,"forks_count":532,"subscribers_count":96,"default_branch":"master","last_synced_at":"2025-01-17T04:46:09.942Z","etag":null,"topics":["deep-learning","gluon","gluonnlp","machine-learning","mxnet","natural-language-generation","natural-language-inference","natural-language-processing","natural-language-understanding","nlg","nlp","nlu","numpy"],"latest_commit_sha":null,"homepage":"https://nlp.gluon.ai/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dmlc.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-04-04T20:57:13.000Z","updated_at":"2025-01-09T16:22:10.000Z","dependencies_parsed_at":"2024-01-08T12:18:02.175Z","dependency_job_id":null,"html_url":"https://github.com/dmlc/gluon-nlp","commit_stats":{"total_commits":838,"total_committers":97,"mean_commits":8.639175257731958,"dds":0.8436754176610979,"last_synced_commit":"14553a0c19790a3b03e8107471c987c7aa4f8faa"},"previous_names":[],"tags_count":20,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmlc%2Fgluon-nlp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmlc%2Fgluon-nlp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmlc%2Fgluon-nlp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmlc%2Fgluon-nlp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dmlc","download_url":"https://codeload.github.com/dmlc/gluon-nlp/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234426836,"owners_count":18830982,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","gluon","gluonnlp","machine-learning","mxnet","natural-language-generation","natural-language-inference","natural-language-processing","natural-language-understanding","nlg","nlp","nlu","numpy"],"created_at":"2024-08-01T08:00:46.689Z","updated_at":"2025-09-27T10:31:52.344Z","avatar_url":"https://github.com/dmlc.png","language":"Python","funding_links":[],"categories":["Deep Learning","implement of BERT besides tensorflow:","\u003ca name=\"NLP\"\u003e\u003c/a\u003e3. NLP","Industrial Strength NLP","Implementations","Python","Libraries","AutoML NLP","Natural Language Processing","Industry Strength NLP","文本数据和NLP","Deep Learning Tools"],"sub_categories":["MXNet","2.14 Misc","Videos and Online Courses","General Purpose NLP","Books"],"readme":"\u003ch2 align=\"center\"\u003e\n\u003ca href=\"https://github.com/dmlc/gluon-nlp\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/dmlc/gluon-nlp/master/docs/_static/gluon-logo.svg\" alt=\"GluonNLP Logo\" width=\"500\"/\u003e\u003c/a\u003e\n\u003c/h2\u003e\n\n\u003ch2 align=\"center\"\u003e\nGluonNLP: Your Choice of Deep Learning for NLP\n\u003c/h2\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://github.com/dmlc/gluon-nlp/actions\"\u003e\u003cimg src=\"https://github.com/dmlc/gluon-nlp/workflows/continuous%20build/badge.svg\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/dmlc/gluon-nlp/actions\"\u003e\u003cimg src=\"https://github.com/dmlc/gluon-nlp/workflows/continuous%20build%20-%20gpu/badge.svg\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://codecov.io/gh/dmlc/gluon-nlp\"\u003e\u003cimg src=\"https://codecov.io/gh/dmlc/gluon-nlp/branch/master/graph/badge.svg\"\u003e\u003c/a\u003e\n    \u003ca href=\"./LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-Apache%202.0-blue.svg\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/dmlc/gluonnlp/actions\"\u003e\u003cimg src=\"https://img.shields.io/badge/python-3.6%2C3.7%2C3.8-blue.svg\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://pypi.org/project/gluonnlp/#history\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/gluonnlp.svg\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nGluonNLP is a toolkit that helps you solve NLP problems. It provides easy-to-use tools that helps you load the text data, \nprocess the text data, and train models.\n\nSee our documents at https://nlp.gluon.ai/master/index.html.\n\n# Features\n\n- Easy-to-use Text Processing Tools and Modular APIs\n- Pretrained Model Zoo\n- Write Models with Numpy-like API\n- Fast Inference via [Apache TVM (incubating)](https://tvm.apache.org/) (Experimental)\n- AWS Integration via [SageMaker](https://aws.amazon.com/sagemaker/)\n\n\n# Installation\nFirst of all, install the MXNet 2 release such as MXNet 2 Alpha. You may use the\nfollowing commands:\n\n```bash\n# Install the version with CUDA 10.2\npython3 -m pip install -U --pre \"mxnet-cu102\u003e=2.0.0a\"\n\n# Install the version with CUDA 11\npython3 -m pip install -U --pre \"mxnet-cu110\u003e=2.0.0a\"\n\n# Install the cpu-only version\npython3 -m pip install -U --pre \"mxnet\u003e=2.0.0a\"\n```\n\n\nTo install GluonNLP, use\n\n```bash\npython3 -m pip install -U -e .\n\n# Also, you may install all the extra requirements via\npython3 -m pip install -U -e .\"[extras]\"\n```\n\nIf you find that you do not have the permission, you can also install to the user folder:\n\n```bash\npython3 -m pip install -U -e . --user\n```\n\nFor Windows users, we recommend to use the [Windows Subsystem for Linux](https://docs.microsoft.com/en-us/windows/wsl/about).\n\n\n# Access the Command-line Toolkits\n\nTo facilitate both the engineers and researchers, we provide command-line-toolkits for\ndownloading and processing the NLP datasets. For more details, you may refer to\n [GluonNLP Datasets](./scripts/datasets) and [GluonNLP Data Processing Tools](./scripts/processing).\n\n```bash\n# CLI for downloading / preparing the dataset\nnlp_data help\n\n# CLI for accessing some common data processing scripts\nnlp_process help\n\n# Also, you can use `python -m` to access the toolkits\npython3 -m gluonnlp.cli.data help\npython3 -m gluonnlp.cli.process help\n\n```\n\n# Run Unittests\nYou may go to [tests](tests) to see how to run the unittests.\n\n\n# Use Docker\nYou can use Docker to launch a JupyterLab development environment with GluonNLP installed.\n\n```\n# GPU Instance\ndocker pull gluonai/gluon-nlp:gpu-latest\ndocker run --gpus all --rm -it -p 8888:8888 -p 8787:8787 -p 8786:8786 --shm-size=2g gluonai/gluon-nlp:gpu-latest\n\n# CPU Instance\ndocker pull gluonai/gluon-nlp:cpu-latest\ndocker run --rm -it -p 8888:8888 -p 8787:8787 -p 8786:8786 --shm-size=2g gluonai/gluon-nlp:cpu-latest\n``` \n\nFor more details, you can refer to the guidance in [tools/docker](tools/docker).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmlc%2Fgluon-nlp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdmlc%2Fgluon-nlp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmlc%2Fgluon-nlp/lists"}