1.huggingface / transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
+9,268 stars
from 159,152 · score 9.13
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
42 repositories by Attention Score · May 7, 2026 – Nov 2, 2026 (UTC)
2.hiyouga / LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
+5,453 stars
from 70,371 · score 8.60
3.stanford-oval / storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
+3,900 stars
from 27,865 · score 8.27
4.google / langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
+3,223 stars
from 36,004 · score 8.08
5.GeeeekExplorer / nano-vllm
Nano vLLM
+3,109 stars
from 13,144 · score 8.04
6.666ghj / BettaFish
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
+2,422 stars
from 40,139 · score 7.79
7.adbar / trafilatura
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
+1,227 stars
from 5,823 · score 7.11
8.argosopentech / argos-translate
Open-source offline translation library written in Python
+737 stars
from 5,881 · score 6.60
9.huggingface / datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
+729 stars
from 21,373 · score 6.59
10.neuml / txtai
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
+656 stars
from 12,402 · score 6.49
11.apachecn / ailearning
AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2
+645 stars
from 41,970 · score 6.47
12.explosion / spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
+634 stars
from 33,376 · score 6.45
13.bigscience-workshop / petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
+633 stars
from 10,046 · score 6.45
14.hankcs / HanLP
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
+430 stars
from 36,102 · score 6.07
15.RasaHQ / rasa
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
+319 stars
from 21,045 · score 5.77
16.nltk / nltk
NLTK Source
+237 stars
from 14,526 · score 5.47
17.microsoft / unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
+226 stars
from 22,012 · score 5.42
18.google-research / bertArchived
TensorFlow code and pre-trained models for BERT
+200 stars
from 39,837 · score 5.30
19.stanfordnlp / stanza
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
+161 stars
from 7,744 · score 5.09
20.piskvorky / gensim
Topic Modelling for Humans
+159 stars
from 16,349 · score 5.08
21.PaddlePaddle / PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
+127 stars
from 12,857 · score 4.85
22.ymcui / Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
+102 stars
from 18,820 · score 4.63
23.huggingface / text-generation-inferenceArchived
Large Language Model Text Generation Inference
+98 stars
from 10,784 · score 4.60
24.flairNLP / flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
+81 stars
from 14,314 · score 4.41
25.ymcui / Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
+72 stars
from 10,160 · score 4.29
26.allenai / scispacy
A full spaCy pipeline and models for scientific/biomedical documents.
+59 stars
from 1,939 · score 4.09
27.readbeyond / aeneas
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
+58 stars
from 2,814 · score 4.08
28.capitalone / DataProfiler
What's in your data? Extract schema, statistics and entities from datasets
+47 stars
from 1,547 · score 3.87
29.jerryji1993 / DNABERT
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
+41 stars
from 742 · score 3.74
30.miso-belica / sumy
Module for automatic summarization of text documents and HTML pages.
+37 stars
from 3,664 · score 3.64
31.allenai / allennlpArchived
An open-source NLP research library, built on PyTorch.
+35 stars
from 11,848 · score 3.58
32.allenai / scibert
A BERT model for scientific text.
+33 stars
from 1,687 · score 3.53
33.keras-team / keras-hub
Pretrained model hub for Keras 3.
+30 stars
from 967 · score 3.43
34.chiphuyen / stanford-tensorflow-tutorialsArchived
This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.
+28 stars
from 10,344 · score 3.37
35.cltk / cltk
The Classical Language Toolkit
+25 stars
from 903 · score 3.26
36.MycroftAI / mycroft-coreArchived
Mycroft Core, the Mycroft Artificial Intelligence platform.
+23 stars
from 6,594 · score 3.18
37.derek73 / python-nameparser
Parse human names into title, given, middle, family, suffix, nickname and maiden name. Typed, zero-dependency, CJK-aware.
+17 stars
from 703 · score 2.89
38.harmonydata / harmony
The Harmony Python library: a research tool for psychologists to harmonise data and questionnaire items. Open source.
+12 stars
from 55 · score 2.56
39.pytorch / textArchived
Models, data loaders and abstractions for language processing, powered by PyTorch
+7 stars
from 3,547 · score 2.08
40.aphp / edsnlp
Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.
+4 stars
from 163 · score 1.61
41.Maluuba / nlg-eval
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
+3 stars
from 1,389 · score 1.39
42.EagleW / PaperRobot
Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
+1 stars
from 478 · score 0.69