chandar-lab

All

31 repositories

crystal-design
Public
Reinforcement Learning for Crystal Structure Design
Python
•0•2•1•1•Updated Dec 5, 2024Dec 5, 2024
AMPLIFY-novel_architectures
Public archive
A fork of AMPLIFY for testing of new architectures for protein language modeling.
Python
•
MIT License
•10•0•0•0•Updated Nov 28, 2024Nov 28, 2024
amp
Public
Python
•
MIT License
•10•0•0•0•Updated Nov 15, 2024Nov 15, 2024
AMPLIFY
Public
Python
•
MIT License
•10•82•1•0•Updated Nov 15, 2024Nov 15, 2024
EfficientLLMs
Public
Python
•1•13•0•0•Updated Jul 30, 2024Jul 30, 2024
SubGoal_Distillation_LLM
Public
Code for paper Sub-goal Distillation: A Method to Improve Small Language Agents, accepted at CoLLAs 2024.
reinforcement-learning transformer decision-transformers llm
Python
•1•3•0•0•Updated Jul 25, 2024Jul 25, 2024
CAIRO
Public
We explain why fairness metrics don't correlate and propose CAIRO to make them correlate.
prompt bias fairness large-language-models fairness-metric
Python
•
MIT License
•0•2•0•0•Updated Jul 10, 2024Jul 10, 2024
CMOptimizer
Public
Python
•
MIT License
•2•5•0•0•Updated Jun 18, 2024Jun 18, 2024
FASP
Public
We study the effect of attention head pruning on fairness in large language models
Jupyter Notebook
•
MIT License
•1•2•0•0•Updated Jun 10, 2024Jun 10, 2024
Recall2Imagine
Public
Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024
reinforcement-learning deep-reinforcement-learning s6 ssm mamba s5 s4 deep-rl model-based-rl state-space-models
Python
•
MIT License
•5•57•5•1•Updated Jun 4, 2024Jun 4, 2024
Lookbehind-SAM
Public
Implementation of Lookbehind-SAM: k steps back, 1 step forward (ICML 2024)
Python
•
Apache License 2.0
•0•0•0•0•Updated May 16, 2024May 16, 2024
RISC
Public
Python
•
MIT License
•1•0•0•0•Updated May 1, 2024May 1, 2024
tgi-for-mila
Public
A toolkit for running text-generation-inference on Mila and Compute Canada
Shell
•
MIT License
•0•2•0•0•Updated Apr 11, 2024Apr 11, 2024
EpiK-Eval
Public
Benchmark to evaluate the capability of language models to consolidate and recall information from multiple training documents.
Python
•
MIT License
•0•5•0•0•Updated Mar 11, 2024Mar 11, 2024
r2i.github.io
Public
JavaScript
•0•0•0•0•Updated Mar 5, 2024Mar 5, 2024
RLHive
Public
Python
•
MIT License
•9•100•23•13•Updated Feb 14, 2024Feb 14, 2024
adaptive-hanabi
Public
Jupyter Notebook
•
MIT License
•0•1•0•0•Updated Feb 5, 2024Feb 5, 2024
INF8250ae-assignments-2023
Public
Python
•0•1•0•0•Updated Nov 14, 2023Nov 14, 2023
INF8245e-assignments-2023
Public
Jupyter Notebook
•0•0•0•0•Updated Nov 8, 2023Nov 8, 2023
COE
Public
Python
•
Apache License 2.0
•1•3•0•0•Updated Jul 13, 2023Jul 13, 2023
CGOptimizer
Public
Python
•
MIT License
•1•4•0•0•Updated Mar 26, 2023Mar 26, 2023
healthy-data-diet
Public
Reduce gender bias in machine learning models.
Python
•
MIT License
•0•2•0•0•Updated Feb 28, 2023Feb 28, 2023
LoCA
Public
reinforcement-learning pytorch model-based-rl
Python
•
MIT License
•1•6•0•4•Updated Feb 15, 2023Feb 15, 2023
IIRC
Public
IIRC: Incremental Implicitly Refined Classification
Python
•
MIT License
•5•30•0•1•Updated Dec 15, 2022Dec 15, 2022
PatchUp
Public
pytorch convolutional-neural-network regularization-methods
Python
•
MIT License
•7•38•0•5•Updated Dec 8, 2022Dec 8, 2022
INF8250e-assignments-public
Public
Jupyter Notebook
•0•1•0•0•Updated Nov 12, 2022Nov 12, 2022
INF8245e-assignments-public
Public
Jupyter Notebook
•1•1•0•0•Updated Oct 27, 2022Oct 27, 2022
RL-Tuner-CP
Public
Java
•1•2•0•0•Updated Sep 7, 2022Sep 7, 2022
LoCA2
Public
Python
•
MIT License
•0•3•0•0•Updated Apr 28, 2022Apr 28, 2022
Lifelong-Hanabi
Public
A Continual Multi-agent RL testbed based on Hanabi
Jupyter Notebook
•
Other
•3•30•1•0•Updated Aug 1, 2021Aug 1, 2021