shizhediao

ChatGPTPapers. Must-read papers, related blogs and API tools on the pre-training and tuning methods for ChatGPT.

active-prompt. Source code for the paper "Active Prompting with Chain-of-Thought for Large Language Models"

R-Tuning. [NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't Know'"

Post-Training-Data-Flywheel. We aim to provide the best references to search, select, and synthesize high-quality and large-quantity data for post-training your LLMs.

Black-Box-Prompt-Learning. Source code for the TMLR paper "Black-Box Prompt Learning for Pre-trained Language Models"

awesome-domain-adaptation-NLP. domain adaptation in NLP

DaVinci. Source code for the paper "Prefix Language Models are Unified Modal Learners"

TILGAN. Source code for the Findings of ACL-IJCNLP 2021 paper entitled "TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation"

automate-cot. Source code for the paper "Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data"

T-DNA. Source code for the ACL-IJCNLP 2021 paper entitled "T-DNA: Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation" by Shizhe Diao et al.

BigGAN-PyTorch-TPU-Distribute. Distributed version (multiple-process) for training BigGAN with TPU.

awesome-transformers. A curated list of resources dedicated to Transformers.

HashTation. Source code for the paper "Hashtag-Guided Low-Resource Tweet Classification"

Doolittle. Source code for the EMNLP 2023 paper entitled "Doolittle: Benchmarks and Corpora for Academic Writing Formalization" by Shizhe Diao et al.

BigGAN-PyTorch-TPU-Single. Single thread version for training BigGAN with TPU.

sequicity. Source code for the ACL 2018 paper entitled "Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures" by Wenqiang Lei et al.

Transformers_TPU. transformers_TPU, trying to solve RAM issues with mapping dataset

SEDST3. SEDST version 3.0 base on the Code for CIKM'18 long paper: Explicit state tracking with semi-supervision for neural dialogue generation.

NeMo-Curator. Scalable data pre processing and curation toolkit for LLMs

shizhediao.github.io. My homepage

BigGAN-PyTorch-TPU-Parallel. Parallel version (multiple-thread) for training BigGAN with TPU.

Human-Contribution-Measurement. Python

PromptPapers. Must-read papers on prompt-based tuning for pre-trained language models.

LLMs-In-China. 中国大模型

nlp_chinese_corpus. 大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

bicvm. BiCVM Code

ZEN. A BERT-based Chinese Text Encoder Enhanced by N-gram Representations

openai-cookbook. Examples and guides for using the OpenAI API

Chain-of-ThoughtsPapers. A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

trl. Train transformer language models with reinforcement learning.

directional-preference-alignment. Directional Preference Alignment

MATH6450-CIFAR10. Course project for MATH6450F training two models onn CIFAR-10 to achieve a good performance. The code is adapted from CIFAR-ZOO (https://github.com/BIGBALLON/CIFAR-ZOO)

Awesome-Chinese-LLM. 整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

HKUST-MPhil-defense-template. TeX

Chinese-Poetry-Generation. RNN-based Chinese Poem Generator