HKU NLP Group

All

22 repositories

STRING
Public
Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"
position-encoding long-context-transformers
Python
•
MIT License
•3•65•1•1•Updated Nov 25, 2024Nov 25, 2024
DiffuLLaMA
Public
DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Python
•3•67•2•1•Updated Nov 22, 2024Nov 22, 2024
diffusion-vs-ar
Public
Code for the paper "Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning"
planning autoregressive diffusion reasoning
Python
•1•24•1•0•Updated Oct 25, 2024Oct 25, 2024
DensePolicy
Public
SAS
•2•0•0•0•Updated Oct 22, 2024Oct 22, 2024
ChunkLlama
Public
[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"
Python
•
Apache License 2.0
•19•368•10•1•Updated Oct 16, 2024Oct 16, 2024
hkunlp.github.io
Public
Website for HKU NLP group (under construction)
JavaScript
•
MIT License
•5•9•0•0•Updated Sep 2, 2024Sep 2, 2024
GSM-Plus
Public
GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.
Python
•5•2•0•0•Updated Jul 8, 2024Jul 8, 2024
GIMLET
Public
The code for GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
Python
•3•2•0•1•Updated Apr 16, 2024Apr 16, 2024
diffusion-of-thoughts
Public
[NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"
machine-learning natural-language-processing text-generation pytorch diffusion-models non-autoregressive mathematical-reasoning chain-of-thought-reasoning diffusion-lm
Python
•2•91•1•0•Updated Feb 24, 2024Feb 24, 2024
RSA
Public
Retrieved Sequence Augmentation for Protein Representation Learning
Python
•4•48•0•0•Updated Nov 1, 2023Nov 1, 2023
SymGen
Public
[EMNLP'23] Code for Generating Data for Symbolic Language with Large Language Models
python bash sql prolog data-generation codex mtop symbolic-language
Python
•
Apache License 2.0
•1•17•0•0•Updated Oct 21, 2023Oct 21, 2023
multilingual-transfer
Public
Code for paper ”Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability“
multilingual bloom transfer llama reasoning llms
Python
•2•15•0•0•Updated Jun 13, 2023Jun 13, 2023
subgoal-theorem-prover
Public
Code for the paper "Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving"
Apache License 2.0
•0•17•1•0•Updated May 25, 2023May 25, 2023
icl-ceil
Public
[ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.
retrieval metric-learning determinantal-point-processes compositionality in-context-learning large-language-models
Python
•
Apache License 2.0
•10•95•3•0•Updated Mar 15, 2023Mar 15, 2023
UnifiedSKGsite
Public
A Portal Site for Structured Knowledge Grounding(SKG) Resources.
SCSS
•
MIT License
•6•9•0•0•Updated Mar 7, 2023Mar 7, 2023
efficient-attention
Public
[EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling
machine-learning machine-translation python3 language-model attention-mechanism vision-transformer pytorch
Python
•
Apache License 2.0
•4•80•0•0•Updated Mar 7, 2023Mar 7, 2023
SunGen
Public
Python
•2•9•0•0•Updated Feb 26, 2023Feb 26, 2023
HumanPrompt
Public
A framework for human-readable prompt-based method with large language models. Specially designed for researchers. (Deprecated, check out LangChain for better usage!)
natural-language-processing large-language-models prompt-engineering
Python
•8•128•0•0•Updated Feb 25, 2023Feb 25, 2023
reparam-discrete-diffusion
Public
Reparameterized Discrete Diffusion Models for Text Generation
machine-learning natural-language-processing text-generation python3 language-model fairseq diffusion-models non-autoregressive pytorch
Python
•
Apache License 2.0
•3•91•4•0•Updated Feb 14, 2023Feb 14, 2023
ProGen
Public
[EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.
data-generation zero-shot-learning influence-functions in-context-learning large-language-models
Python
•0•25•0•0•Updated Feb 4, 2023Feb 4, 2023
.github
Public
0•2•0•0•Updated Apr 20, 2022Apr 20, 2022
ZeroGen
Public
[EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.
Python
•10•16•0•0•Updated Feb 18, 2022Feb 18, 2022