zhangxy-2019's repositories
TransformerLens
A library for mechanistic interpretability of GPT-style language models
long-form-factuality
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
bonito
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
promptbench
A unified evaluation framework for large language models
Multimodal-AND-Large-Language-Models
Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.
ReAlign
Reformatted Alignment
wikiextractor
A tool for extracting plain text from Wikipedia dumps
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
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.
LLM-Factuality-Survey
The repository for the survey paper <<Survey on Large Language Models Factuality: Knowledge, Retrieval and Domain-Specificity>>
OpenLLaMA2
DeepSpeed+Ray based LLaMA2 PT/RLHF/RS training framework
llama
Inference code for LLaMA models
research-course
"How to Do Great Research" Course for Ph.D. Students
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
prm800k
800,000 step-level correctness labels on LLM solutions to MATH problems
CUHK-PhD-Thesis-Template
Latex template for CUHK PhD Thesis
FastChat
An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.
Megatron-LM
Ongoing research training transformer models at scale
lantern
Lantern官方版本下载 蓝灯 翻墙 代理 科学上网 外网 加速器 梯子 路由 - Быстрый, надежный и безопасный доступ к открытому интернету - lantern proxy vpn censorship-circumvention censorship gfw accelerator پراکسی لنترن، ضدسانسور، امن، قابل اعتماد و پرسرعت
IC-DST
Code base of In-Context Learning for Dialogue State tracking
icl-selective-annotation
[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"
superset
Apache Superset is a Data Visualization and Data Exploration Platform
Awesome_Few_Shot_Learning
Advances of few-shot learning, especially for NLP applications.
transfer-learning-conv-ai
🦄 State-of-the-Art Conversational AI with Transfer Learning
latex_paper_writing_tips
Tips for Writing a Research Paper using LaTeX
TextualExplInContext
The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning (NeurIPS 2022)