1,993 dependents
| Package | Description | Downloads/month |
|---|---|---|
| tiktoken is a fast BPE tokeniser for use with OpenAI's models. | 150.6M | |
| 🤗 Transformers: the model-definition framework for state-of-the-art machine lear... | 141.8M | |
| NLTK Source | 59.9M | |
| CloudFormation Linter | 54.9M | |
| python parser for human readable dates | 36.5M | |
| A parser for HCL2 | 12.2M | |
| A modular SQL linter and auto-formatter with support for multiple dialects and t... | 9.5M | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio gener... | 8.2M | |
| Framework for orchestrating role-playing, autonomous AI agents. By fostering col... | 7.4M | |
| DSPy: The framework for programming—not prompting—language models | 7.1M | |
| The fastest pure-Python PEG parser I can muster | 6.4M | |
| Convert documents to structured data effortlessly. Unstructured is open-source E... | 5.2M | |
| ✨ HTML Template Linter and Formatter. Django - Jinja - Nunjucks - Handlebars - G... | 5.2M | |
| An open-source framework for detecting, redacting, masking, and anonymizing sens... | 4.5M | |
| Find dates inside text using Python and get back datetime objects | 4.1M | |
| Reference BLEU implementation that auto-downloads test sets and reports a versio... | 4M | |
| A Python based Bicep parser | 3.5M | |
| An open source implementation of CLIP. | 3.1M | |
| Python port of Moses tokenizer, truecaser and normalizer | 2.6M | |
| Parse docker image as distribution does. | 2.4M | |
| CLI tool to build, test, debug, and deploy Serverless applications using AWS SAM | 2.3M | |
| Our library for RL environments + evals | 2.3M | |
| Semantic link for Microsoft Fabric | 2.3M | |
| Fastapi mail system sending mails(individual, bulk) attachments(individual, bulk... | 1.7M | |
| A simple HTML content extractor in Python. Can be run as a wrapper for Mozilla's... | 1.6M | |
| Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt... | 1.4M | |
| Access a database of word frequencies, in various natural languages. | 1.4M | |
| Excel formulas interpreter in Python. | 928K | |
| aider is AI pair programming in your terminal | 864K | |
| Unicode Standard tokenization routines and orthography profile segmentation | 846K | |
| A modular SQL linter and auto-formatter with support for multiple dialects and t... | 675K | |
| A Python port of Textile, A humane web text generator | 652K | |
| Check for stylistic and formal issues in .rst and .py files included in the docu... | 590K | |
| Command line interface to read and write keys/values to/from toml files | 577K | |
| Convert PDF to markdown + JSON quickly with high accuracy | 566K | |
| Super fast semantic router for AI decision making | 562K | |
| Lightweight piece tokenization library | 528K | |
| Low footprint C/C++ CBOR library and Python tool providing code generation from ... | 524K | |
| Universal Romanizer that can convert any unicode script to roman (latin) script | 514K | |
| Deep Learning for humans | 467K | |
| A python package for whisper normalizer | 454K | |
| Grapheme-to-Phoneme transductions that preserve input and output indices, and su... | 429K | |
| For WER | 414K | |
| G2P engine for TTS | 401K | |
| CleverCSV is a Python package for handling messy CSV files. It provides a drop-i... | 399K | |
| Jobs scraper library for LinkedIn, Indeed, Glassdoor, Google, ZipRecruiter & mor... | 394K | |
| A unified library of SOTA model optimization techniques like quantization, pruni... | 376K | |
| A plugin for pyang that creates Python bindings for a YANG model. | 328K | |
| 💬 Open source machine learning framework to automate text- and voice-based con... | 314K |
