changyong93

nlp-arxiv-daily

Automatically Update NLP Papers Daily using Github Actions (ref: https://github.com/Vincentqyw/cv-arxiv-daily)

torchtune

PyTorch native finetuning library

uv

An extremely fast Python package and project manager, written in Rust.

mamba

Mamba SSM architecture

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention)

lobe-chat

🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Azure / DeepSeek), Knowledge Base (file upload / knowledge management / RAG ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT/ Claude application.

AutoRAG

AutoML tool for RAG

fast-jsonl

Fast JSONL line-by-line reading.

Kor-IR

Kor-IR: Korean Information Retrieval Benchmark

LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

misspelling

맞춤법 검사기 with GPT4

tokencost

Easy token price estimates for 400+ LLMs. TokenOps.

Sophia

The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

FLEUR

[ACL 2024] FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model

recurrentgemma

Open weights language model from Google DeepMind, based on Griffin.

awesome-llm-apps

Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

Prompt2Sign

The Data and Code of Prompt2Sign: A Comprehensive Multilingual Sign Language Superset.

bookmarks

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

unsloth

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

langchain-kr

LangChain 공식 Document, Cookbook, 그 밖의 실용 예제를 바탕으로 작성한 한국어 튜토리얼입니다. 본 튜토리얼을 통해 LangChain을 더 쉽고 효과적으로 사용하는 방법을 배울 수 있습니다.

open-korean-instructions

언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.

LLaMA3_cookbook

Here's how to use Lama3 for beginners and what services are being used.

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

lm-format-enforcer

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

Awesome-LLM-Uncertainty-Reliability-Robustness

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

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

ollama

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

multimodal

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.