[ICLR 2024] Domain-Agnostic Molecular Generation with Chemical Feedback

Jupyter widget to interactively view molecular structures and trajectories

Official repository for discrete Walk-Jump Sampling (dWJS)

ARAGOG- Advanced RAG Output Grading. Exploring and comparing various Retrieval-Augmented Generation (RAG) techniques on AI research papers dataset. Includes modular code for easy experimentation an…

pyFoldX: python bindings for FoldX.

Tools for merging pretrained large language models.

A set of utilities for running few-shot prompting experiments on large-language models

Code for paper "LEVER: Learning to Verifiy Language-to-Code Generation with Execution" (ICML'23)

TemStaPro - a program for protein thermostability prediction using sequence representations from a protein language model.

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

LLM training code for Databricks foundation models

Inference code and configs for the ReplitLM model family

The MATH Dataset (NeurIPS 2021)

Benchmarks for Model-Based Optimization

[EMNLP 2023, Findings] GRACE: Discriminator-Guided Chain-of-Thought Reasoning

RL algorithm: Advantage induced policy alignment

[NIPS2023] RRHF & Wombat

Reproduction of "RLCD Reinforcement Learning from Contrast Distillation for Language Model Alignment

Reference implementation for DPO (Direct Preference Optimization)

Data Files for "Deep diversification of an AAV capsid protein by machine learning"

Bioinformatics code for paper associated with deep diversification of AAV

Official release of the ProGen models

The official implementation of the Molecule Attention Transformer.

The page with all info about SOTA text detoxification models and datasets.

A curated list of reinforcement learning with human feedback resources (continually updated)

Success and Failure Linguistic Simplification Annotation 💃

ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.