daun-io

Daun's starred repositories

LogicKor

한국어 언어모델 다분야 사고력 벤치마크

Language:Python10900

gazelle

Joint speech-language model - respond directly to audio!

Language:PythonApache-2.027400

JudgeLM

An open-sourced LLM judge for evaluating LLM-generated answers.

Language:PythonApache-2.027300

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonMIT1888600

BitNet-Transformers

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

Language:Python24300

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookMIT1789400

exllamav2

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

Language:PythonMIT310400

convex-backend

Open source single-machine version of the Convex backend

Language:RustNOASSERTION65400

edm

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

Language:PythonNOASSERTION114000

AI-Self-Training-DPO-SDXL

Unofficial implementation. Stable diffusion model trained by AI Feedback-Based Self-Training Direct Preference Optimization.

Language:Python5300

TCD

Official Repository of the paper "Trajectory Consistency Distillation"

Language:Python27600

PixArt-alpha

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Language:PythonAGPL-3.0238800

sd-webui-supermerger

model merge extention for stable diffusion web ui

Language:PythonAGPL-3.069000

latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Language:PythonMIT416600

react-grid-gallery

Justified image gallery component for React

Language:TypeScriptMIT96400

Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. Orion-14B 系列模型包括一个具有140亿参数的多语言基座大模型以及一系列相关的衍生模型，包括对话模型，长文本模型，量化模型，RAG微调模型，Agent微调模型等。

Language:PythonApache-2.077100

llama.cpp

LLM inference in C/C++

Language:C++MIT5986700

Typoon

A text expander that fully supports Korean letters as well. 한글을 제대로 지원하는 텍스트 확장기.

Language:C++GPL-3.05400

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Language:PythonMIT89600

openroleplay.ai

openroleplay.ai is an open source character.ai alternative.

Language:TypeScriptAGPL-3.012200

u0.wtf

브랜드를 알리는 짧은 URL, U0 (Dub을 기반으로 합니다.)

Language:TypeScriptAGPL-3.0300

whisper.cpp

Port of OpenAI's Whisper model in C/C++

Language:CMIT3239100

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Language:PythonMIT328600

ml-mobileone

This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone".

Language:SwiftNOASSERTION68600

shorten-url

Magic Teleport - Shorten URL with Vercel KV

Language:JavaScriptMIT1900

Awesome-LLM-Uncertainty-Reliability-Robustness

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

MIT54100

so-vits-svc

SoftVC VITS Singing Voice Conversion

Language:PythonAGPL-3.02440900

private-gpt

Interact with your documents using the power of GPT, 100% privately, no data leaks

Language:PythonApache-2.05257000

prompt-engineering

Tips and tricks for working with Large Language Models like OpenAI's GPT-4.

MIT809400

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Language:PythonMIT948500