Morizeyao

text-generation-webui

A Gradio web UI for Large Language Models.

LLaMA-Factory

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

clash-verge

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

LLaVA

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

triton

Development repository for the Triton language and compiler

MiniCPM-V

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

micrograd

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

open_clip

An open source implementation of CLIP.

minbpe

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

Qwen2

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

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

gpt-fast

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

promptbase

All things prompt engineering

mergekit

Tools for merging pretrained large language models.

OLMo

Modeling, training, eval, and inference code for OLMo

torchtune

A Native-PyTorch Library for LLM Fine-tuning

LapisCV

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

DeBERTa

The implementation of DeBERTa

datatrove

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

instructor-embedding

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

Telechat

open-instruct

cookbook

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

EasyContext

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

YuLan-Chat

YuLan: An Open-Source Large Language Model

Aurora

🐳 Aurora is a [Chinese Version] MoE model. Aurora is a further work based on Mixtral-8x7B, which activates the chat capability of the model's Chinese open domain.

fm-cheatsheet

Website for hosting the Open Foundation Models Cheat Sheet.

MachineLearningFAQ

Machine Learning FAQ

hf-trim

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