LouChao98's repositories
AutoCompressors
Adapting Language Models to Compress Long Contexts
CoLT5-attention
Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch
Diffusion-LM
Diffusion-LM
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
graph_ensemble_learning
Graph Ensemble Learning
easy-oa
Chrome extension for OA sites like arxiv, openreivew: 1. PDF back to abstract page, 2. Rename PDF page with paper title.
easy-to-hard
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
GaLore
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
lambeq
A high-level Python library for Quantum Natural Language Processing
landmark-attention
Landmark Attention: Random-Access Infinite Context Length for Transformers
lightning
Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.
llama-moe
⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
lp-sparsemap
LP-SparseMAP: Differentiable sparse structured prediction in coarse factor graphs
non_neg
Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning
parserllm
Use context-free grammars with an LLM
picard
PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models. PICARD is a ServiceNow Research project that was started at Element AI.
Pushdown-Layers
Code for Pushdown Layers from our EMNLP 2023 paper
stack-attention
Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"
transformer_grammars
Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale, TACL (2022)