awesome-llama: https://github.com/PaddlePaddle/PaddleNLP
bert compression distributed-training document-intelligence embedding ernie information-extraction llama llm neural-search nlp paddlenlp pretrained-models question-answering search-engine semantic-analysis sentiment-analysis transformers uie
Score: 27.151913053625204
Last synced: about 9 hours ago
JSON representation
Repository metadata:
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- Host: GitHub
- URL: https://github.com/PaddlePaddle/PaddleNLP
- Owner: PaddlePaddle
- License: apache-2.0
- Created: 2021-02-05T13:07:42.000Z (almost 5 years ago)
- Default Branch: develop
- Last Pushed: 2025-12-17T09:19:22.000Z (about 2 months ago)
- Last Synced: 2026-01-13T16:49:55.589Z (22 days ago)
- Topics: bert, compression, distributed-training, document-intelligence, embedding, ernie, information-extraction, llama, llm, neural-search, nlp, paddlenlp, pretrained-models, question-answering, search-engine, semantic-analysis, sentiment-analysis, transformers, uie
- Language: Python
- Homepage: https://paddlenlp.readthedocs.io
- Size: 112 MB
- Stars: 12,899
- Watchers: 97
- Forks: 3,070
- Open Issues: 476
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING_en.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
Owner metadata:
- Name: PaddlePaddle
- Login: PaddlePaddle
- Email:
- Kind: organization
- Description:
- Website: http://paddlepaddle.org
- Location:
- Twitter:
- Company:
- Icon url: https://avatars.githubusercontent.com/u/23534030?v=4
- Repositories: 85
- Last Synced at: 2023-02-27T13:30:46.845Z
- Profile URL: https://github.com/PaddlePaddle
GitHub Events
Total
- Commit comment event: 1
- Create event: 68
- Delete event: 46
- Fork event: 198
- Issue comment event: 3813
- Issues event: 573
- Member event: 9
- Pull request event: 2734
- Pull request review comment event: 1372
- Pull request review event: 2117
- Push event: 1013
- Release event: 4
- Watch event: 800
- Total: 12748
Last Year
- Commit comment event: 1
- Create event: 68
- Delete event: 46
- Fork event: 198
- Issue comment event: 3817
- Issues event: 575
- Member event: 9
- Pull request event: 2734
- Pull request review comment event: 1372
- Pull request review event: 2117
- Push event: 1013
- Release event: 4
- Watch event: 802
- Total: 12756
Committers metadata
Last synced: 17 days ago
Total Commits: 5,692
Total Committers: 379
Avg Commits per committer: 15.018
Development Distribution Score (DDS): 0.941
Commits in past year: 544
Committers in past year: 109
Avg Commits per committer in past year: 4.991
Development Distribution Score (DDS) in past year: 0.93
| Name | Commits | |
|---|---|---|
| Zhong Hui | z****t@g****m | 335 |
| Sijun He | s****e@h****m | 265 |
| Linjie Chen | 4****c | 241 |
| lugimzzz | 6****z | 226 |
| 骑马小猫 | 1****6@q****m | 216 |
| w5688414 | w****4@g****m | 212 |
| Jack Zhou | z****e@b****m | 203 |
| wawltor | f****4@h****m | 199 |
| Jiaqi Liu | 7****0@q****m | 198 |
| yujun | 5****u | 181 |
| liu zhengxi | 3****8@q****m | 178 |
| smallv0221 | 3****1 | 160 |
| Zeyu Chen | c****1@b****m | 154 |
| Weiguo Zhu | D****9@g****m | 138 |
| gongenlei | g****l@q****m | 126 |
| Noel | w****3@b****m | 124 |
| Siming Dai | 9****6@q****m | 118 |
| yingyibiao | y****6@1****m | 116 |
| Liujie0926 | 4****6 | 72 |
| westfish | w****h@1****m | 68 |
| zhang junjun | 1****1@q****m | 67 |
| Guo Sheng | g****g@b****m | 66 |
| tianxin | t****4@b****m | 65 |
| Ting Liu | w****n@f****m | 61 |
| Yuanle Liu | y****e@1****m | 51 |
| Steffy-zxf | 4****f | 46 |
| chenxujun | c****c | 41 |
| kinghuin | k****l@1****m | 40 |
| chenxiaozeng | c****7@b****m | 39 |
| Milen | 3****0 | 36 |
| and 349 more... | ||
Issue and Pull Request metadata
Last synced: 26 days ago
Total issues: 1,455
Total pull requests: 5,777
Average time to close issues: 7 months
Average time to close pull requests: about 1 month
Total issue authors: 947
Total pull request authors: 353
Average comments per issue: 2.95
Average comments per pull request: 1.9
Merged pull request: 3,451
Bot issues: 0
Bot pull requests: 1
Past year issues: 130
Past year pull requests: 1,985
Past year average time to close issues: about 2 months
Past year average time to close pull requests: 6 days
Past year issue authors: 101
Past year pull request authors: 142
Past year average comments per issue: 1.66
Past year average comments per pull request: 1.54
Past year merged pull request: 1,136
Past year bot issues: 0
Past year bot pull requests: 0
Top Issue Authors
- cqray1990 (19)
- ZTurboX (13)
- goldwater668 (13)
- dingidng (12)
- gggdroa (10)
- zhaogf01 (10)
- tianchiguaixia (9)
- liuzhipengchd (9)
- BEILOP (8)
- ZHUI (7)
- hitzhu (7)
- Wong4j (7)
- natureLanguageQing (6)
- sanbuphy (6)
- wojiaoshihua (6)
Top Pull Request Authors
- DrownFish19 (314)
- ZHUI (298)
- DesmonDay (290)
- lugimzzz (217)
- SylarTiaNII (149)
- Liujie0926 (136)
- w5688414 (132)
- yuanlehome (123)
- JunnYu (120)
- zhangbo9674 (115)
- sneaxiy (111)
- wtmlon (96)
- wj-Mcat (92)
- ForFishes (80)
- blacksheep-Aristotle (79)
Top Issue Labels
- question (931)
- stale (551)
- triage (451)
- bug (322)
- others (50)
- documentation (24)
- pipelines (7)
- text classification (5)
- enhancement (4)
- ppdiffusers (3)
- keep (3)
- ie (3)
- LLM (2)
- model-compression (2)
- Enterprise (2)
- sentiment-analysis (2)
- FAQ (2)
- contributor (2)
- hackathon (2)
- uie-x (1)
- taskflow (1)
- help wanted (1)
- installation (1)
- pre-training (1)
- data augmentation (1)
Top Pull Request Labels
- contributor (818)
- stale (549)
- HappyOpenSource (69)
- Beijing Innovation Consortium (28)
- pipelines (26)
- status: proposed (23)
- hackathon (14)
- XPU (13)
- enhancement (7)
- QA (6)
- faster (6)
- neural-search (5)
- skip-ci: distribute-a100 (4)
- Trainer (4)
- 多硬件 (4)
- status: accepted (4)
- documentation (4)
- question (3)
- 易用性 (3)
- skip-ci: distribute-v100 (3)
- inference (3)
- question answering (3)
- ie (2)
- model-compression (2)
- triage (2)
- status: not progressed (2)
- deploy (1)
- question generation (1)
- bug (1)
- dependencies (1)
Package metadata
- Total packages: 9
-
Total downloads:
- pypi: 120,887 last-month
- Total docker downloads: 799
- Total dependent packages: 19 (may contain duplicates)
- Total dependent repositories: 454 (may contain duplicates)
- Total versions: 222
- Total maintainers: 2
pypi.org: paddlenlp
Easy-to-use and powerful NLP library with Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including Neural Search, Question Answering, Information Extraction and Sentiment Analysis end-to-end system.
- Homepage: https://github.com/PaddlePaddle/PaddleNLP
- Documentation: https://paddlenlp.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 2.8.1 (published over 1 year ago)
- Last Synced: 2026-01-19T17:26:19.047Z (16 days ago)
- Versions: 96
- Dependent Packages: 15
- Dependent Repositories: 438
- Downloads: 108,938 Last month
- Docker Downloads: 799
-
Rankings:
- Forks count: 0.221%
- Stargazers count: 0.244%
- Dependent repos count: 0.684%
- Dependent packages count: 0.962%
- Average: 0.981%
- Downloads: 1.779%
- Docker downloads count: 1.994%
- Maintainers (1)
pypi.org: fast-tokenizer-python
PaddleNLP Fast Tokenizer Library written in C++
- Homepage: https://github.com/PaddlePaddle/PaddleNLP/fast_tokenizer
- Documentation: https://fast-tokenizer-python.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 1.0.2 (published almost 3 years ago)
- Last Synced: 2026-01-16T18:39:55.394Z (19 days ago)
- Versions: 4
- Dependent Packages: 2
- Dependent Repositories: 14
- Downloads: 199 Last month
-
Rankings:
- Forks count: 0.22%
- Stargazers count: 0.243%
- Dependent packages count: 3.242%
- Average: 3.329%
- Dependent repos count: 3.914%
- Downloads: 9.028%
- Maintainers (1)
proxy.golang.org: github.com/paddlepaddle/paddlenlp
- Homepage:
- Documentation: https://pkg.go.dev/github.com/paddlepaddle/paddlenlp#section-documentation
- Licenses: apache-2.0
- Latest release: v2.8.1+incompatible (published over 1 year ago)
- Last Synced: 2026-01-16T18:40:06.930Z (19 days ago)
- Versions: 49
- Dependent Packages: 0
- Dependent Repositories: 0
-
Rankings:
- Dependent packages count: 6.999%
- Average: 8.173%
- Dependent repos count: 9.346%
proxy.golang.org: github.com/PaddlePaddle/PaddleNLP
- Homepage:
- Documentation: https://pkg.go.dev/github.com/PaddlePaddle/PaddleNLP#section-documentation
- Licenses: apache-2.0
- Latest release: v2.8.1+incompatible (published over 1 year ago)
- Last Synced: 2026-01-16T18:40:16.187Z (19 days ago)
- Versions: 49
- Dependent Packages: 0
- Dependent Repositories: 0
-
Rankings:
- Dependent packages count: 6.999%
- Average: 8.173%
- Dependent repos count: 9.346%
pypi.org: paddle-pipelines
Paddle-Pipelines: An End to End Natural Language Proceessing Development Kit Based on PaddleNLP
- Homepage: https://github.com/PaddlePaddle/PaddleNLP
- Documentation: https://paddle-pipelines.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 0.6.2 (published about 2 years ago)
- Last Synced: 2026-01-16T18:40:09.398Z (19 days ago)
- Versions: 11
- Dependent Packages: 0
- Dependent Repositories: 1
- Downloads: 86 Last month
-
Rankings:
- Forks count: 0.22%
- Stargazers count: 0.243%
- Dependent packages count: 7.306%
- Average: 8.621%
- Downloads: 13.258%
- Dependent repos count: 22.077%
- Maintainers (1)
pypi.org: tool-helpers
Data tool helpers for PaddleNLP pre-training.
- Homepage: https://github.com/PaddlePaddle/PaddleNLP/blob/develop/model_zoo/ernie-1.0/data_tools
- Documentation: https://tool-helpers.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 0.1.2 (published over 1 year ago)
- Last Synced: 2026-01-16T18:40:06.983Z (19 days ago)
- Versions: 3
- Dependent Packages: 1
- Dependent Repositories: 0
- Downloads: 9,910 Last month
-
Rankings:
- Stargazers count: 0.294%
- Forks count: 0.341%
- Dependent packages count: 6.633%
- Average: 11.585%
- Downloads: 20.046%
- Dependent repos count: 30.611%
- Maintainers (1)
pypi.org: faster-tokenizer
PaddleNLP Faster Tokenizer Library written in C++
- Homepage: https://github.com/PaddlePaddle/PaddleNLP/faster_tokenizer
- Documentation: https://faster-tokenizer.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 0.2.0 (published over 3 years ago)
- Last Synced: 2026-01-16T18:39:52.105Z (19 days ago)
- Versions: 7
- Dependent Packages: 1
- Dependent Repositories: 0
- Downloads: 127 Last month
-
Rankings:
- Stargazers count: 0.294%
- Forks count: 0.341%
- Dependent packages count: 6.633%
- Average: 12.253%
- Downloads: 23.384%
- Dependent repos count: 30.611%
- Maintainers (1)
pypi.org: faster-tokenizers
PaddleNLP Faster Tokenizer Library written in C++
- Homepage: https://github.com/PaddlePaddle/PaddleNLP/faster_tokenizers
- Documentation: https://faster-tokenizers.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 0.1.1 (published over 3 years ago)
- Last Synced: 2026-01-16T18:40:00.758Z (19 days ago)
- Versions: 2
- Dependent Packages: 0
- Dependent Repositories: 1
- Downloads: 26 Last month
-
Rankings:
- Forks count: 0.22%
- Stargazers count: 0.243%
- Dependent packages count: 7.306%
- Average: 13.199%
- Dependent repos count: 22.077%
- Downloads: 36.148%
- Maintainers (1)
pypi.org: fast-dataindex
Data tool helpers for PaddleNLP pre-training.
- Homepage: https://github.com/PaddlePaddle/PaddleNLP/blob/develop/model_zoo/ernie-1.0/data_tools
- Documentation: https://fast-dataindex.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 0.1.2 (published over 1 year ago)
- Last Synced: 2026-01-16T18:39:54.286Z (19 days ago)
- Versions: 1
- Dependent Packages: 0
- Dependent Repositories: 0
- Downloads: 1,601 Last month
-
Rankings:
- Dependent packages count: 10.31%
- Average: 34.168%
- Dependent repos count: 58.026%
- Maintainers (1)
Dependencies
- actions/checkout v3 composite
- actions/setup-python v1 composite
- actions/checkout v3 composite
- actions/setup-python v1 composite
- actions/checkout v2 composite
- actions/setup-python v1 composite
- actions/stale v6.0.1 composite
- actions/checkout v3 composite
- actions/setup-python v1 composite
- codecov/codecov-action v3 composite
- paddlepaddle/paddlenlp pipelines-cpu-1.0 build
- docker.elastic.co/elasticsearch/elasticsearch 8.3.3
- paddlepaddle/paddlenlp pipelines-1.0-gpu-cuda10.2-cudnn7
- docker.elastic.co/elasticsearch/elasticsearch 8.3.3
- paddlepaddle/paddlenlp pipelines-cpu-1.0
- com.android.support.constraint:constraint-layout 1.1.3 implementation
- com.android.support:appcompat-v7 28.0.0 implementation
- com.android.support:design 28.0.0 implementation
- org.jetbrains:annotations 15.0 implementation
- junit:junit 4.12 testImplementation
- com.android.support:appcompat-v7 28.0.0 implementation
- junit:junit 4.13.2 testImplementation
- com.android.support.constraint:constraint-layout 1.1.3 implementation
- com.android.support:appcompat-v7 28.0.0 implementation
- com.android.support:design 28.0.0 implementation
- org.jetbrains:annotations 15.0 implementation
- junit:junit 4.12 testImplementation
- hnswlib >=0.5.2
- numpy >=1.17.2
- paddle-serving-app >=0.7.0
- paddle-serving-client >=0.7.0
- paddle-serving-server-gpu >=0.7.0.post102
- paddlenlp >=2.1.1
- paddlepaddle-gpu >=2.2.3
- pandas ==0.25.1
- pybind11 *
- pymilvus >=2.1.0
- visualdl >=2.2.2
- hnswlib >=0.5.2
- numpy >=1.17.2
- paddlenlp >=2.3.7
- paddlepaddle-gpu >=2.2.3
- pandas ==0.25.1
- pybind11 *
- pymilvus >=2.1.0
- visualdl >=2.2.2
- hnswlib >=0.5.2
- paddlenlp >=2.3.7
- pandas ==0.25.1
- pybind11 *
- pymilvus ==1.1.1
- onnxruntime *
- paddle2onnx >=1.0.3
- paddlenlp >=2.4.3
- paddlepaddle >=2.4rc
- psutil *
- onnx *
- onnxconverter-common *
- onnxruntime-gpu *
- paddle2onnx >=1.0.3
- paddlenlp >=2.4.3
- paddlepaddle-gpu >=2.4rc
- psutil *
- hnswlib >=0.5.2
- numpy >=1.17.2
- paddle-serving-app >=0.7.0
- paddle-serving-client >=0.7.0
- paddle-serving-server-gpu >=0.7.0.post102
- paddlenlp >=2.3.4
- paddlepaddle-gpu >=2.3.0
- pandas ==0.25.1
- pybind11 *
- pymilvus ==1.1.2
- visualdl >=2.2.2
- onnxruntime *
- paddle2onnx >=1.0.3
- paddlenlp >=2.4.3
- paddlepaddle >=2.4rc
- psutil *
- onnx *
- onnxconverter-common *
- onnxruntime-gpu *
- paddle2onnx >=1.0.3
- paddlenlp >=2.4.3
- paddlepaddle-gpu >=2.4rc
- psutil *
- hnswlib >=0.5.2
- numpy >=1.17.2
- paddle-serving-app >=0.7.0
- paddle-serving-client >=0.7.0
- paddle-serving-server-gpu >=0.7.0.post102
- paddlenlp >=2.3.4
- paddlepaddle-gpu >=2.3.0
- pandas ==0.25.1
- pybind11 *
- pymilvus ==1.1.2
- visualdl >=2.2.2
- onnxruntime *
- paddle2onnx >=1.0.3
- paddlenlp >=2.4.3
- paddlepaddle >=2.4rc
- psutil *
- onnx *
- onnxconverter-common *
- onnxruntime-gpu *
- paddle2onnx >=1.0.3
- paddlenlp >=2.4.3
- paddlepaddle-gpu >=2.4rc
- psutil *
- hnswlib >=0.5.2
- paddlenlp >=2.3.7
- pandas ==0.25.1
- pybind11 *
- pymilvus ==1.1.2
- Markdown <3.4
- jinja2 ==3.0.3
- paddlepaddle >=2.2.2,<2.4.0
- readthedocs-sphinx-search ==0.1.0
- sphinx ==3.5.2
- sphinx-copybutton ==0.3.1
- sphinx-markdown-tables ==0.0.15
- sphinx_rtd_theme ==0.5.2
- fastapi ==0.79.0
- openai ==0.8.0
- pydantic ==1.9.1
- python-dotenv ==0.20.0
- regex ==2022.6.2
- sse_starlette ==0.10.3
- uvicorn ==0.17.6
- importlib_metadata *
- nltk *
- paddlenlp *
- tabulate *
- visualdl *
- progress ==1.6
- attrdict *
- pyyaml *
- subword_nmt *
- nvgpu >=0.9.0
- regex >=2021.11.10
- spacy >=2.3.7
- tqdm >=4.62.3
- visualdl >=2.2.2
- evaluate ==0.2.2
- nltk ==3.6.2
- evaluate ==0.2.2
- nltk ==3.6.2
- tqdm ==4.64.0
- faiss ==1.5.3
- hnswlib ==0.6.2
- numpy ==1.22.4
- paddle ==1.0.2
- paddlenlp ==2.3.4
- paddlepaddle ==2.3.1
- regex ==2022.7.25
- spacy ==3.4.1
- tqdm ==4.64.0
- PyYAML ==5.4.1
- attrdict ==2.0.1
- jieba ==0.42.1
- subword-nmt ==0.3.7
- websocket-client ==1.0.1
- PyYAML ==5.4.1
- attrdict ==2.0.1
- jieba ==0.42.1
- subword_nmt ==0.3.7
- pypinyin *
- nltk ==3.6.2
- rouge_score ==0.0.4
- configparser ==5.2.0
- nltk ==3.6.7
- numpy ==1.21.0
- py-rouge ==1.1
- tqdm ==4.62.3
- nltk *
- progressbar *
- pymysql *
- sqlparse *
- LAC *
- asdl *
- attrs *
- cn2an *
- jsonnet *
- networkx *
- nvgpu *
- pyrsistent *
- sentencepiece *
- setproctitle *
- tqdm *
- paddlenlp *
- paddlepaddle-gpu ==2.2.0
- torch >=1.7
- transformers *
- paddlenlp >=2.2.0
- tensorflow_text ==2.5.0
- transformer ==4.11.3
- datasets *
- h5py *
- multiprocess *
- numpy *
- paddlenlp *
- scipy *
- tqdm *
- wandb *
- onnxruntime ==1.10.0
- psutil *
- onnx ==1.12.0
- onnxconverter-common ==1.9.0
- onnxruntime-gpu ==1.11.1
- psutil *
- paddleocr *
- editdistance >=0.6.0
- opencv-python >=4.6.0.66
- hyperopt >=0.2.5
- ray >=2.0
- click ==8.0
- elasticsearch >=7.7,<=7.10
- faiss-cpu >=1.7.2
- fastapi *
- langdetect *
- markdown *
- mmh3 *
- more_itertools *
- nltk *
- numba *
- opencv-contrib-python-headless *
- opencv-python >=4.4
- paddlenlp >=2.4.3
- paddleocr *
- pdfplumber *
- pydantic *
- pymilvus >=2.1
- python-docx *
- python-multipart *
- requests *
- sqlalchemy >=1.4.2,<2
- sqlalchemy_utils *
- st-annotated-text *
- streamlit ==1.11.1
- uvicorn *
- wordcloud ==1.8.2.2
- fast_tokenizer_python * development
- paddlepaddle >=2.4.1 development
- parameterized * development
- pre-commit * development
- pytest * development
- pytest-cov * development
- pytest-xdist * development
- regex * development
- Flask-Babel <3.0.0
- colorama *
- colorlog *
- datasets >=2.0.0
- dill <0.3.5
- fastapi *
- huggingface_hub >=0.11.1
- jieba *
- multiprocess <=0.70.12.2
- paddle2onnx *
- paddlefsl *
- protobuf >=3.1.0,<=3.20.0
- rich *
- sentencepiece *
- seqeval *
- tqdm *
- typer *
- uvicorn *
- visualdl *
- GPUtil *
- PyYAML ==5.4.1
- attrdict ==2.0.1
- bce-python-sdk *
- beautifulsoup4 *
- cma *
- coverage *
- fast_tokenizer_python *
- h5py *
- lac *
- nltk *
- opencv-contrib-python ==4.6.0.66
- opencv-python ==4.6.0.66
- packaging *
- paddleocr *
- pandas *
- parameterized *
- psutil *
- pybind11 *
- pycryptodome *
- pynvml *
- pypinyin *
- pyrouge *
- pytest *
- regex *
- scikit-learn *
- subword_nmt ==0.3.7
- visualdl *
- yacs *
- zstandard *
- fast_tokenizer_python * test
- parameterized * test
- regex * test
- sentencepiece * test
- torch >=1.5 test
- transformers * test
- actions/checkout v3 composite
- actions/setup-python v4 composite
- rouge ==1.0.1
- rouge ==1.0.1
- cupy-cuda116 *
- pybind11 *
- bitsandbytes ==0.39.0
- datasets ==2.12.0
- deepspeed ==0.9.4
- sentencepiece *
- torch ==2.0.1
- transformers ==4.30.2
- fast-tokenizer-python *
- paddlenlp >=2.5.1
- paddlepaddle >=2.4.1
- pyarrow *
- python >=3.7
- Pillow ==9.3.0
- blobfile ==1.3.3
- colorama ==0.4.5
- colorlog ==6.6.0
- numpy >=1.19.5,<=1.21.6
- omegaconf ==2.2.2
- opencv-python >=4.2.0.32
- pybind11 ==2.10.0
- regex ==2022.7.25
- requests ==2.25.1
- tqdm >=4.62.1
- datasets *
- mteb *
- typer ==0.9.0
- PyMuPDF ==1.20.2
- arxiv *
- erniebot *
- gradio ==3.41.2
- scipdf *
- paddlepaddle >=2.4.1 test
- pytest * test