QinLuo's repositories
composer
Train neural networks up to 7x faster
datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
llm-foundry
LLM training code for MosaicML foundation models
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
chemnlp
ChemNLP project
hakkero
The Hakkero, also known as the Eight Trigram Furnace, was a magical furnace that the Jade Emperor used to purify his Golden Elixir.
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.
LOMO
LOMO: LOw-Memory Optimization
Megatron-LM
Ongoing research training transformer models at scale
MiniGPT-4
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
MOSS
An open-source tool-augmented conversational language model from Fudan University
Mr.-Ranedeer-AI-Tutor
A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.
open_flamingo
An open-source framework for training large multimodal 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.
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
streaming
A Data Streaming Library for Efficient Neural Network Training
text-generation-webui
A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.
tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
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
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
WizardLM
Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder
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.