Stars
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
🖱 A JavaScript library for interactively picking DOM elements
Die Datenbank öffentlicher Sprecher des HBI
Llama-3 agents that can browse the web by following instructions and talking to you
🌐 The Internet OS! Free, Open-Source, and Self-Hostable.
🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…
A library for efficient similarity search and clustering of dense vectors.
🔭 R package for Preprocessing and Analyzing Web Tracking Data
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.
The 4CAT Capture and Analysis Toolkit provides modular data capture & analysis for a variety of social media platforms.
Find and fix bugs in natural language machine learning models using adaptive testing.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Turn expensive prompts into cheap fine-tuned models
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A Python script that aggregates recent popular posts from your Mastodon timeline
Python package for statistical data animations
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Repository for Frequency Word List Generator and processed files
A python library for decision tree visualization and model interpretation.
news-please - an integrated web crawler and information extractor for news that just works