thenx

awesome-public-real-time-datasets

A list of publicly available datasets with real-time data maintained by the team at bytewax.io

GlaDOS

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

mistral.rs

Blazingly fast LLM inference.

KRAGEN

Software to implement GoT with a weviate vectorized database

MoMA

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

llama3

The official Meta Llama 3 GitHub site

Hermes-Function-Calling

uni2ts

[ICML2024] Unified Training of Universal Time Series Forecasting Transformers

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

sdxs

Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"

talk-llama-fast

Port of OpenAI's Whisper model in C/C++ with xtts and wav2lip

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Video-LLaVA

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

llm.c

LLM training in simple, raw C/CUDA

GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

LLocalSearch

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

llamafile

Distribute and run LLMs with a single file.

DiJiang

[ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear attention mechanism.

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 minute to run.

BitMat

An efficent implementation of the method proposed in "The Era of 1-bit LLMs"

LlamaAcademy

A school for camelids

VoiceCraft

Zero-Shot Speech Editing and Text-to-Speech in the Wild

dspy

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

localpilot

OOTDiffusion

Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

dioxus

Fullstack app framework for web, desktop, mobile, and more.

awesome-large-action-model

Awesome Large Action Model (LAM): Models that could help gets things done.

LocalAI

:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed inference

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model