SmolLM2: A tiny yet mighty 147M LLaMA-style model with RoPE, GQA, and SwiGLU — built for speed and efficiency."

LLaMA 2 implemented from scratch in PyTorch

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Code for the paper "ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?"

[Nature Communications] The official code for "Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases".

Code repository for the framework to engage in clinical decision making task using the MIMIC-CDM dataset.

Code repository to create the MIMIC-CDM Dataset.

[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

A Paper collection for LLM based Patient Simulators

Code for ECAI'25-Generating Clinically Realistic EHR Data via a Hierarchy- and Semantics-Guided Transformer

repository for Publicly Available Clinical BERT Embeddings

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Code for TMM-HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization

Open Synthea patient data for machine learning and team training.

Generating synthetic Electronic Health Records using continuous-time diffusion models.

A benchmark for few-shot evaluation of foundation models for electronic health records (EHRs)

Electronic Health Record Analysis with Python.

Code repository for the paper : Causal thinking for decision making on Electronic Health Records: why and how

EMNLP'22 | PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning

PyTrial: A Comprehensive Platform for Artificial Intelligence for Drug Development

Med-BERT, contextualized embedding model for structured EHR data

Deep Generative Modelling of Patient Timelines using Electronic Health Records

Code for BEHRT: Transformer for Electronic Health Records

A simple and efficient Mamba implementation in pure PyTorch and MLX.