🪢 Open source LLM engineering platform: Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

A framework for the evaluation of autoregressive code generation language models.

Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

The blessed GitHub Action, for publishing your 📦 distribution files to PyPI: https://github.com/marketplace/actions/pypi-publish

Code and data of We-Math

Modern, extensible Python project management

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Dynamically provisioning persistent local storage with Kubernetes

A fast MoE impl for PyTorch

LLM101n: Let's build a Storyteller

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

Code for the paper titled "Instruction Tuning With Loss Over Instructions"

Retrying library for Python

Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.

LangStream. Event-Driven Developer Platform for Building and Running LLM AI Apps. Powered by Kubernetes and Kafka.

Offical code for the CVPR 2024 Paper: Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language

Blazingly fast LLM inference.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Implementation for MatMul-free LM.

Video+code lecture on building nanoGPT from scratch

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Kubernetes spawner for JupyterHub

HF🤗每日简报机器人

OpenGFW is a flexible, easy-to-use, open source implementation of GFW (Great Firewall of China) on Linux

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

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

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"