Neko9810

minbpe

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

awesome-model-transferability-estimation

A collection of model transferability estimation methods.

StableCascade

Official Code for Stable Cascade

CLIP_models

LongLM

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

gpt-fast

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

Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

gptstore-prompts

Here are the Top 100 prompts on GPTStore, which we can use to learn and improve prompt engineering.

InfoBatch

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

buildVpn

图文教程搭建一个vpn翻墙

run

润学全球官方指定GITHUB，整理润学宗旨、纲领、理论和各类润之实例；解决为什么润，润去哪里，怎么润三大问题； 并成为新**人的核心宗教，核心信念。

TrustLLM

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

factool

FacTool: Factuality Detection in Generative AI

depyf

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

jiant

jiant is an nlp toolkit

multidiffusion-upscaler-for-automatic1111

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

KgCoOp

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

mixture-of-experts

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

llama2.c

Inference Llama 2 in one file of pure C

dreamgaussian4d

[arXiv 2023] DreamGaussian4D: Generative 4D Gaussian Splatting

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

supervision

We write your reusable computer vision tools. 💜

Wonder3D

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

longformer

Longformer: The Long-Document Transformer

smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.