LAION-AI / medical
This repository will be a summary and outlook on all our open, medical, AI advancements.
☆29Updated last year
Related projects ⓘ
Alternatives and complementary repositories for medical
- Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmind☆52Updated last month
- Implementation of Metaformer, but in an autoregressive manner☆23Updated 2 years ago
- My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other h…☆51Updated last year
- ☆52Updated last year
- Minimal implementation of multiple PEFT methods for LLaMA fine-tuning☆13Updated last year
- A repository to house some personal attempts to beat some state-of-the-art for medical datasets☆97Updated 11 months ago
- ☆73Updated last year
- Contrastive Language-Image Pretraining☆37Updated 4 months ago
- Utilities for PyTorch distributed☆23Updated last year
- Code for reproducing the experiments on large-scale pre-training and transfer learning for the paper "Effect of large-scale pre-training …☆18Updated 2 years ago
- A case study of efficient training of large language models using commodity hardware.☆68Updated 2 years ago
- Implementation of LogAvgExp for Pytorch☆32Updated 2 years ago
- [WIP] A 🔥 interface for running code in the cloud☆86Updated last year
- Another attempt at a long-context / efficient transformer by me☆37Updated 2 years ago
- Embedding Recycling for Language models☆38Updated last year
- Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️☆52Updated last year
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆46Updated 3 months ago
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- HomebrewNLP in JAX flavour for maintable TPU-Training☆46Updated 9 months ago
- Implementation of a holodeck, written in Pytorch☆17Updated last year
- ☆29Updated 2 weeks ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆43Updated last month
- ☆49Updated last year
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated last year
- Implementation of Nyström Self-attention, from the paper Nyströmformer☆122Updated 9 months ago
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆72Updated 3 months ago
- Quickest way to share everything about your research within a single app☆17Updated 9 months ago