amelie-schreiber Goto Github PK
Name: Amelie Schreiber
Type: User
Bio: Independent researcher and mathematician, working on protein language models, certain equivariant transformers, Low Rank Adaptations, and QLoRA
Name: Amelie Schreiber
Type: User
Bio: Independent researcher and mathematician, working on protein language models, certain equivariant transformers, Low Rank Adaptations, and QLoRA
Detecting anomalous texts with persistent homology of context vectors computed by individual attention heads in language transformers
Studying how well the persistent homology of collocations and keyphrases are preserved by various models.
Experiments with ChatGPT
Confidence bootstrapping for DiffDock
Comparing different models' preservation of persistent homology.
Protein Design by Machine Learning guided Directed Evolution
A repo for persistent homology analysis of ideas in vision transformers, using the attention mechanism to derive the Jensen-Shannon distance between probability distributions associated to tokens.
Training a Low Rank Adaptation of the protein language model ESM-2 for RNA binding site predictor
Trying to train LoRAs for ESM-2
Various Ideas for Protein Masked LM with ESMFold/ESM-2
Generation of protein sequences and evolutionary alignments via discrete diffusion models
Directed evolution of proteins in sequence space with gradients
NeurIPS 2023 Spotlight paper: Full atom protein pocket design via iterative refinement
(Unofficial) GET for proteins
Persistent homology of context vectors computed by individual attention heads in Hebrew language models
Some ideas and code for LoRA models (Low Rank Adaptation)
We study the persistent homology of the context vectors computed by individual attention heads in multilingual language models
Some PEFT models for PPI prediction and symmetry prediction.
Target Sequence-Conditioned Generation of Peptide Binders via Masked Language Modeling
Persistent homology analysis of individual attention heads in transformer models
Code and Data for the paper: Multi-level Protein Structure Pre-training with Prompt Learning [ICLR 2023]
Repository for Protein-Vec, a protein embedding mixture of experts model
Some scoring functions for predicting the effects of mutations on protein sequences using ESM-2
Quantum Surface Codes
Using variations on Gibbs sampling for directed evolution
Diffusion model for generating small molecules
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.