gabrielmbmb

thiserror

derive(Error) for struct and enum error types

HVM

A massively parallel, optimal functional runtime in Rust

Bend

A massively parallel, high-level programming language

awesome-synthetic-datasets

awesome synthetic (text) datasets

lerobot

🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch

fastfit

FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes

candle-ext

An extension library to Candle that provides PyTorch functions not currently available in Candle

cohere-toolkit

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

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

ratchet

A cross-platform browser ML framework.

deepeval

The LLM Evaluation Framework

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

SWE-agent

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 1.5 minutes to run.

StringZilla

Up to 10x faster strings for C, C++, Python, Rust, and Swift, leveraging SWAR and SIMD on Arm Neon and x86 AVX2 & AVX-512-capable chips to accelerate search, sort, edit distances, alignment scores, etc 🦖

faster-fifo

Faster alternative to Python's multiprocessing.Queue (IPC FIFO queue)

data-is-better-together

Let's build better datasets, together!

transformer-heads

Toolkit for attaching, training, saving and loading of new heads for transformer models

distilabel-spin-dibt

Repository containing the SPIN experiments on the DIBT 10k ranked prompts

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

gutenberg

Scraper for downloading the entire ebooks repository of project Gutenberg

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

fsdp_qlora

Training LLMs with QLoRA + FSDP

text-clustering

Easily embed, cluster and semantically label text datasets

solara

A Pure Python, React-style Framework for Scaling Your Jupyter and Web Apps

LLM-Blender

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

sympy

A computer algebra system written in pure Python

vertex-ai-huggingface

🤗 Collection of examples on how to train, deploy and monitor HuggingFace models in Google Cloud Vertex AI

mpi4py

Python bindings for MPI

sora-mini