yguo33

MoA

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

Yi-1.5

Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.

llama3

The official Meta Llama 3 GitHub site

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

outlines

Structured Text Generation

FuseAI

FuseAI Project

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

mergekit

Tools for merging pretrained large language models.

NEFTune

Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

LLaMA2-Accessory

An Open-source Toolkit for LLM Development

Chinese-Mixtral-8x7B

中文Mixtral-8x7B（Chinese-Mixtral-8x7B）

notebooks

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

code-server

VS Code in the browser

Mr.-Ranedeer-AI-Tutor

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

AgentVerse

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

SwiftInfer

Efficient AI Inference & Serving

facefusion

Next generation face swapper and enhancer

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

mlx

MLX: An array framework for Apple silicon

blog

Public repo for HF blog posts

MixtralKit

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

detect-pretrain-code-contamination

open-instruct