Bailin

gated_linear_attention. Python

tensor2struct-public. Semantic parsers based on encoder-decoder framework

grammar-prompting. Grammar Prompting for Domain-Specific Language Generation with Large Language Models

seq_icl. Jupyter Notebook

SA-Sent. Implementation for SA-LSTM

nest-trans-em18. Code for "A Neural Transition-based Model for Nested Mention Recognition"

MemNN. Implementation of Memory Network in pyTorch

overlapping-ner-em18. Implementation of Neural Segmental Hypergraph

weaksp_em19. Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs(EMNLP2019)

btg-seq2seq. Python

disco_em19. A Neural Two-Stage Approach for Recognizing Discontiguous Entities (EMNLP 2019)

traffic-counting. little traffic couting tool based on qt,bgs,cvblob

dgmaml-semparse.

Megatron-LM. Ongoing research training transformer models at scale

seq-test. Understand and test language model architectures on synthetic tasks.

flash-linear-attention. Fast implementations of causal linear attention for autogressive language modeling (Pytorch)

serving. A flexible, high-performance serving system for machine learning models

covert-channel. covert-channel based on IPID

arduino. Arduino

Jekyll-translation. Jekyll-translation