Nealcly's starred repositories
CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Megatron-LM
Ongoing research training transformer models at scale
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
text-generation-inference
Large Language Model Text Generation Inference
Automated-Fact-Checking-Resources
Links to conference/journal publications in automated fact-checking (resources for the TACL22/EMNLP23 paper).
detect-gpt
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
neural-Jacana
This is the code for neural-Jacana aligner, and the data for MultiMWA dataset.
EditScorer
The code for EMNLP2022 paper "Improved grammatical error correction by ranking elementary edits"
Cross-Align
EMNLP2022 "Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment"
GLUE-X
We leverage 14 datasets as OOD test data and conduct evaluations on 8 NLU tasks over 21 popularly used models. Our findings confirm that the OOD accuracy in NLP tasks needs to be paid more attention to since the significant performance decay compared to ID accuracy has been found in all settings.