QinLuo's repositories
BMInf
Efficient Inference for Big Models
BMTrain
Efficient Training (including pre-training and fine-tuning) for Big Models
CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model
ControlNet
Let us control diffusion models
CPM-Live
Live Training for Open-source Big Models
EnergonAI
Large-scale model inference.
flash-attention
Fast and memory-efficient exact attention
human-eval
Code for the paper "Evaluating Large Language Models Trained on Code"
knowledge-graph-from-GPT-3
Using GPT-3 to organize and access information, and generate questions. Long term goal is to make an agent-like research assistant.
LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
Lila
A unified benchmark for math reasoning
MNBVC
MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T网页数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。
natural-instructions
Expanding natural instructions
Omnigrok
Omnigrok: Grokking Beyond Algorithmic Data
open_flamingo
An open-source framework for training large multimodal models
Prompt-Engineering-Guide
:octopus: Guides, papers, lecture, and resources for prompt engineering
ReAct
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
reflexion
Reflexion: an autonomous agent with dynamic memory and self-reflection
serge
A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.
setl
A simple Spark-powered ETL framework that just works 🍺
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
text-generation-webui
A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.
Transnormer
[EMNLP 2022] Official implementation of Transnormer in our EMNLP 2022 paper - The Devil in Linear Transformer
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
unlocking-the-power-of-llms
使用 Prompts 和 Chains 让 ChatGPT 成为神奇的生产力工具！
z-bench
Z-Bench 1.0 by 真格基金：一个麻瓜的大语言模型中文测试集。Z-Bench is a LLM prompt dataset for non-technical users, developed by an enthusiastic AI-focused team in Zhenfund.