Pinned Repositories
allennlp
An open-source NLP research library, built on PyTorch.
hybrid-preferences
Learning to route instances for Human vs AI Feedback
natural-instructions
Expanding natural instructions
open-instruct
AllenAI's post-training codebase
llm-temporal-alignment
Methods and evaluation for aligning language models temporally
self-instruct
Aligning pretrained language models with instruction data generated by themselves.
StageDP
A two-stage RST discourse parser
TagNN-PDTB
Tag-enhanced Tree-Structured NN for discourse relation classification.
Tk-Instruct
Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.
WikiQA-Selection
Answer selection task based on WikiQA datatest.
yizhongw's Repositories
yizhongw/self-instruct
Aligning pretrained language models with instruction data generated by themselves.
yizhongw/Tk-Instruct
Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.
yizhongw/StageDP
A two-stage RST discourse parser
yizhongw/llm-temporal-alignment
Methods and evaluation for aligning language models temporally
yizhongw/truthfulqa_reeval
yizhongw/tf-qanet
Tensorflow implementation of QANet.
yizhongw/allennlp-reading-comprehension-research
yizhongw/FLAN-data-generation
yizhongw/promptsource
Toolkit for collecting and applying prompts
yizhongw/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
yizhongw/yizhongw.github.io
My Homepage.
yizhongw/cracking-the-data-science-interview
A Collection of Cheatsheets, Books, Questions, and Portfolio For DS/ML Interview Prep
yizhongw/ds-cheatsheets
List of Data Science Cheatsheets to rule the world
yizhongw/EasyLM
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
yizhongw/KILT
Library for Knowledge Intensive Language Tasks
yizhongw/natural-instructions
Expanding natural instructions
yizhongw/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
yizhongw/YoudaoTranslator
Alfred Youdao Translate Workflow
yizhongw/allennlp
An open-source NLP research library, built on PyTorch.
yizhongw/bi-att-flow
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.
yizhongw/blog
My Blog.
yizhongw/FActScore
A package to evaluate factuality of long-form generation. Original implementation of "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"
yizhongw/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
yizhongw/helm
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
yizhongw/knnlm
yizhongw/open-instruct-bk
yizhongw/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
yizhongw/reward-bench
RewardBench: the first evaluation tool for reward models.
yizhongw/SciDTB
SciDTB: Discourse Dependency TreeBank for Scientific Abstracts
yizhongw/wechat_articles_spider
微信公众号文章的爬虫