HKUNLP/reparam-discrete-diffusion

Stars
30
Rank 839,658 (Top 17 %)
Language
Python
License
Apache License 2.0
Created almost 2 years ago
Updated almost 2 years ago

HKUNLP/reparam-discrete-diffusion

HKUNLP

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Reparameterized Discrete Diffusion Models for Text Generation

UnifiedSKG

[EMNLP 2022] A Unified Framework and Analysis for Structured Knowledge Grounding with Text-to-Text Language Models

instructor-embedding

One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Binder

[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"

DS-1000

[ICML 2023] Official data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".

HumanPrompt

A framework for human-readable prompt-based method with large language models. Specially designed for researchers. (In progress)

diffusion-of-thoughts

Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"

icl-selective-annotation

[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"

efficient-attention

[EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling

icl-ceil

Code for our paper “Compositional Exemplars for In-context Learning”.

STRING

Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"

batch-prompting

A simple prompting approach that enables the LLMs to run inference in batches.

subgoal-theorem-prover

Code for the paper "Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving"

ProGen

[EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.

hkunlp.github.io

Website for HKU NLP group (under construction)

diagrams_toolkit

Source code for diagrams in the paper of NLPers from HKU.

ChunkLlama

Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

SymGen

Code for Generating Data for Symbolic Language with Large Language Models

.github

diffusion-vs-ar