Morizeyao

lorax

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

FFXVIFix

A fix for Final Fantasy XVI that adds ultrawide/narrower support, uncaps framerate in cutscenes, lets you adjust gameplay FOV and much more.

MemoRAG

Empowering RAG with a memory-based data interface for all-purpose applications!

clash-verge-rev

Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)

Qwen2.5

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

LapisCV

📃 开箱即用的 Markdown 简历，支持 VSCode / Obsidian / Typora

hf-trim

Reduce the size of pretrained Hugging Face models via vocabulary trimming.

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

open-instruct

OLMo

Modeling, training, eval, and inference code for OLMo

torchtune

A Native-PyTorch Library for LLM Fine-tuning

cookbook

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

VisCPM

[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

DeBERTa

The implementation of DeBERTa

clash-verge

A Clash GUI based on tauri. Supports Windows, macOS and Linux.

fm-cheatsheet

Website for hosting the Open Foundation Models Cheat Sheet.

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

triton

Development repository for the Triton language and compiler

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

LLaVA

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

open_clip

An open source implementation of CLIP.

mergekit

Tools for merging pretrained large language models.

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

Telechat

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

MachineLearningFAQ

Machine Learning FAQ