A package for easily working with US and state metadata

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

WIP

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

LLM-Merging: Building LLMs Efficiently through Merging

Code for Discovering Preference Optimization Algorithms with and for Large Language Models

DSPy: The framework for programming—not prompting—foundation models

Prompt design using JSX.

🙌 OpenHands: Code Less, Make More

Puzzles for learning Triton

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

Development repository for the Triton language and compiler

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

Print-friendly, minimalist CV page

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

A Blazing Fast AI Gateway with integrated Guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Machine Learning Engineering Open Book

Robust recipes to align language models with human and AI preferences

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

A public release of TimelineBuilder for building personal digital data timelines.