sustcsonglin

disco-pointer

Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span Selection

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

flash-linear-rnn

Implementations of various linear RNN layers using pytorch and triton

gated_linear_attention_layer

mamba-triton

pointer-net-for-nested

The official implementation of ACL2022``Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks''

second-order-neural-dmv

source code of COLING2020 "Second-Order Unsupervised Neural Dependency Parsing"

span-based-dependency-parsing

Source code of ACL2022 "Headed-Span-Based Projective Dependency Parsing" and "Combining (second-order) graph-based and headed-span-based projective dependency parsing

TN-LCFRS

Official Implementation of ACL2023: Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars

TN-PCFG

source code of NAACL2021 "PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols“ and ACL2021 main conference "Neural Bilexicalized PCFG Induction"

sustcsonglin/flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

sustcsonglin/TN-PCFG

source code of NAACL2021 "PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols“ and ACL2021 main conference "Neural Bilexicalized PCFG Induction"

sustcsonglin/flash-linear-rnn

Implementations of various linear RNN layers using pytorch and triton

sustcsonglin/mamba-triton

sustcsonglin/gated_linear_attention_layer

sustcsonglin/disco-pointer

Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span Selection

sustcsonglin/FlagAttention

A collection of memory efficient attention operators implemented in the Triton language.

sustcsonglin/lit-gpt

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

sustcsonglin/cuda-playground

sustcsonglin/mamba.py

An efficient Mamba implementation in PyTorch and MLX.

sustcsonglin/nanokitchen

Parallel Associative Scan for Language Models

sustcsonglin/safari

Convolutions for Sequence Modeling

sustcsonglin/stk

sustcsonglin/streaming-llm

Efficient Streaming Language Models with Attention Sinks

sustcsonglin/sustcsonglin.github.io

:page_facing_up: Elegant & friendly homepage (bio, tech portfolio, resume, doc...) template with Markdown and VuePress

sustcsonglin/sustcsonglin_old.github.io

:page_facing_up: Elegant & friendly homepage (bio, tech portfolio, resume, doc...) template with Markdown and VuePress

sustcsonglin/TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

sustcsonglin/transformers_ssm_copy

sustcsonglin/zoology

Understand and test language model architectures on synthetic tasks.

sustcsonglin/Academic-project-page-template

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

sustcsonglin/BeamTreeRecursiveCells

sustcsonglin/cutlass-kernels

sustcsonglin/hyena-dna

Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena

sustcsonglin/m2

Monarch Mixer

sustcsonglin/mamba

sustcsonglin/S5

sustcsonglin/s5-pytorch

Pytorch implementation of Simplified Structured State-Spaces for Sequence Modeling (S5)

sustcsonglin/SGEMM_CUDA

Fast CUDA matrix multiplication from scratch

sustcsonglin/stack-attention

Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"

sustcsonglin/state-spaces

Sequence Modeling with Structured State Spaces