pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

pytensor

PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

python

School projects in Python that use the arcade library (http://arcade.academy/)

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

qserve

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

radio

Official repository for "AM-RADIO: Reduce All Domains Into One"

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

rank_llm

Repository for prompt-decoding using LLMs (GPT3.5, GPT4, Vicuna, and Zephyr)

rccl-tests

RCCL Performance Benchmark Tests

real-time-voice-cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

reprover

Retrieval-Augmented Theorem Provers for Lean

ringattention

Transformers with Arbitrarily Large Context

rlx

A reinforcement learning framework based on MLX.

rock-scissors-paper-molerat

rock-scissors-paper-molerat created by GitHub Classroom

rocm

AMD ROCm™ Software - GitHub Home

rpg_svo_pro_open

rubikscubeai

rwkv-cuda

The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )

samba

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

screenshot-to-code

Drop in a screenshot and convert it to clean HTML/Tailwind/JS code

sd-forge-layerdiffuse

[WIP] Layer Diffusion for WebUI (via Forge)

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

self-improving-language-models

A more compressed take on Meta's recent paper: https://arxiv.org/abs/2401.10020

self-organising-systems

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

seqax

seqax = sequence modeling + JAX

sequoia

scalable and robust tree-based speculative decoding algorithm

skyvern

Automate browser-based workflows with LLMs and Computer Vision

slamesh

The official implementation of SLAMesh.

smfft

fast Fourier transform on GPU in shared memory for AstroAccelerate project