SLMs for personal expenses summaries

Open-source Platform for Scientific and Technical Data Processing and Visualization

Fork of the Triton language and compiler for Windows support and easy installation

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Github action to print relevant stats about Pull Request reviewers

Open-Source Frontier Voice AI

A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.

🌱 EcoLogits tracks the energy consumption and environmental footprint of using generative AI models through APIs.

A framework for optimizing DSPy programs with RL

A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models

An Awesome list of curated DSPy resources.

Official Code for ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users (NeurIPS 2024)

A collection of resources on attacks and defenses targeting text-to-image diffusion models

Red-Teaming Language Models with DSPy

DSPydantic: Auto-Optimize Your Pydantic Models with DSPy

MITRE LILAC(TM) toolkit for detecting and mitigating problematic chatbot responses

🪄 Interpreto is an interpretability toolbox for LLMs

A framework for efficient model inference with omni-modality models

🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

Unified Schema-Based Information Extraction

💫 Toolkit to help you get started with Spec-Driven Development

Run pytest against markdown files/docstrings.

Guardrails to support any-agent

Fully automatic censorship removal for language models

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Nearly Inference Free Embeddings: make your RAG queries 500x faster

Chat with your images using Black Forest Lab's FLUX.1 Kontext

Pytorch VQA : Visual Question Answering (https://arxiv.org/pdf/1505.00468.pdf)