KaiQiangSong

openai-python

The official Python library for the OpenAI API

gpt-crawler

Crawl a site to generate knowledge files to create your own custom GPT from a URL

flash-attention

Fast and memory-efficient exact attention

LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

text-generation-inference

Large Language Model Text Generation Inference

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

FasterTransformer

Transformer related optimization, including BERT, GPT

lm-evaluation-harness

A framework for few-shot evaluation of language models.

awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

mPLUG-Owl

mPLUG-Owl & mPLUG-Owl2: Modularized Multimodal Large Language Model

Pix2Text

An Open-Source Python3 tool for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

LOMO

LOMO: LOw-Memory Optimization

PandaGPT

[TLLM'23] PandaGPT: One Model To Instruction-Follow Them All

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

transformers-bloom-inference

Fast Inference Solutions for BLOOM

Megatron-LLM

distributed trainer for LLMs

MathPile

Generative AI for Math: MathPile

LEval

[ACL'24] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark

ChromaPalette

LLaMA-Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

InfoBench

VCSum

Dataset for Findings of ACL 23 "VCSum: A Versatile Chinese Meeting Summarization Dataset"

MeetingBank-utils

zebra-inference

FOLNet

This repository includes the code for First-Order Logic Network (FOLNet).

user-engaging-headlines

rankboostplus

Implementations of various ranking-by-boosting algorithms including Rankboost+.

InfoBench

transformers-bloom-inference

Fast Inference Solutions for BLOOM