A pipeline for LLM knowledge distillation

[ACL 2024 Findings] Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning

Let's create synthetic textbooks together :)

Generate textbook-quality synthetic LLM pretraining data

Korean Math Word Problems

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

개인적으로 수집한 한국어 NLP용 말뭉치 모음

한국어 뉴스의 긍정, 부정이 레이블링 된 금융 뉴스 문장 감성 분석 데이터셋 (finance sentiment corpus) 입니다.

RL algorithm: Advantage induced policy alignment

Korea Investment & Securities Open API Github https://apiportal.koreainvestment.com

A Gradio web UI for Large Language Models with support for multiple inference backends.

Example models using DeepSpeed

Self-Alignment with Principle-Following Reward Models

All-in-one text de-duplication

Fast and memory-efficient exact attention

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

42dot LLM consists of a pre-trained language model, 42dot LLM-PLM, and a fine-tuned model, 42dot LLM-SFT, which is trained to respond to user prompts and supports both languages simultaneously by t…

Measuring Massive Multitask Language Understanding | ICLR 2021

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

High-Resolution Image Synthesis with Latent Diffusion Models

Kill Zscaler without password or jail Zscaler in a virtual machine

KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)

A framework for few-shot evaluation of language models.