Bringing bio (molecules and more) to the Hugging Face Datasets library

AIDE: the state-of-the-art machine learning engineer agent, generating machine learning solution code from natural language descriptions.

Open-source AI chatbot app that anonymizes personal information

An extremely fast Python package and project manager, written in Rust.

Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.

Make triton easier

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

BigCodeBench: Benchmarking Code Generation Towards AGI

Convert all of libgen to high quality markdown

GPT4V-level open-source multi-modal model based on Llama3-8B

Open-source BI for engineers

The modern replacement for Jupyter Notebooks

Titan Core - Snowflake infrastructure-as-code. Provision environments, automate deploys, CI/CD. Manage RBAC, users, roles, and data access. Declarative Python Resource API. Change Management tool f…

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

Define configs using Python dataclasses and override them on the CLI

Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)

Kernel-based statistical tests to check if data is drawn from any distribution in a parametric family

Fork of chatarena: add examples that help to study the manipulation capabilities of LLMs

A concise but complete full-attention transformer with a set of promising experimental features from various papers

source code of the paper: DAG LEARNING ON THE PERMUTAHEDRON

Implementation for ReFactor GNNs

CSuite: A Suite of Benchmark Datasets for Causality

Latest Weight Averaging (NeurIPS HITY 2022)

Evolution Strategies in JAX 🦎

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch

Hackable and optimized Transformers building blocks, supporting a composable construction.

An index of algorithms for learning causality with data