← Back to catalog

hf_ehr Assess

HuggingFace-native framework for training large language models on structured electronic health records using the MEDS (Medical Event Data Standard) format. Ships pretrained autoregressive foundation models — GPT, Llama, Mamba, and Hyena architectures — trained from scratch on 2 billion tokens of de-identified structured EHR data from Stanford Health Care. Designed for researchers already in the HuggingFace ecosystem who want to fine-tune or benchmark EHR foundation models without custom pipelines. Complementary to FEMR: FEMR covers masked/CLMBR-style training; hf_ehr covers autoregressive HuggingFace-native training. FEMR's own documentation recommends hf_ehr for autoregressive CLMBR-style models. Apache 2.0. From the Shah Lab at Stanford Medicine.

Judgement: Assess

Assess — permissive licence (Apache-2.0).

Derived deterministically by the MACH scorer from the signals below — not written prose.

Repository

Dormant — last commit ~13 mo ago; has releases

★ 55 stars · 10 forks · 6 open issues

Jupyter Notebook 91% Python 8% Shell 1%

Signals & lineage

Every value records the source it was harvested from.

FieldValueSource
descriptionTraining HuggingFace models on EHR datagithub_api
discovered_condanot_founddiscovery
discovered_crannot_founddiscovery
discovered_doinot_founddiscovery
discovered_hfStanfordShahLab/gpt-base-512-clmbr,StanfordShahLab/gpt-base-1024-clmbr,StanfordShahLab/gpt-base-2048-clmbr,StanfordShahLab/gpt-base-4096-clmbr,StanfordShahLab/llama-base-512-clmbr,StanfordShahLab/llama-base-1024-clmbr,StanfordShahLab/llama-base-2048-clmbr,StanfordShahLab/llama-base-4096-clmbr,StanfordShahLab/mamba-tiny-1024-clmbr,StanfordShahLab/mamba-tiny-4096-clmbr,StanfordShahLab/mamba-tiny-8192-clmbr,StanfordShahLab/mamba-tiny-16384-clmbr,StanfordShahLab/hyena-large-1024-clmbr,StanfordShahLab/hyena-large-4096-clmbr,StanfordShahLab/hyena-large-8192-clmbr,StanfordShahLab/hyena-large-16384-clmbrdiscovery
discovered_npmnot_founddiscovery
discovered_pypihf_ehrdiscovery
has CIFalsegithub_api
has docsTruegithub_api
has releasesTruegithub_api
has testsFalsegithub_api
HuggingFace downloads (monthly)not_foundhuggingface
judgementAssessmach_scorer
judgement reasonAssess — permissive licence (Apache-2.0).mach_scorer
licenseApache-2.0github_api
PyPI downloads (monthly)61pypi
archivedFalsegithub_api
repository created2023-10-05T07:36:06Zgithub_api
GitHub forks10github_api
repo healthDormantmach_health
repo health reasonlast commit ~13 mo ago; has releasesmach_health
homepagehttps://arxiv.org/abs/2412.16178github_api
languagesJupyter Notebook:91,Python:8,Shell:1github_api
last commit2025-11-02T04:11:51Zgithub_api
open issues6github_api
primary languageJupyter Notebookgithub_api
repo_size_kb21021github_api
GitHub stars55github_api
topicselectronic-health-records,foundation-models,healthcare,machine-learninggithub_api

Change history

Recorded deviations — when a harvested value changed between runs.

WhenFieldWasNowSource
2026-11-20T21:53:45.625404repo_health—Dormantmach_health
2026-11-20T21:53:45.625404repo_health_reason—last commit ~13 mo ago; has releasesmach_health
2026-11-20T21:53:45.625314judgement—Assessmach_scorer
2026-11-20T21:53:45.625314judgement_reason—Assess — permissive licence (Apache-2.0).mach_scorer
2026-11-20T21:49:06.290050hf_downloads——huggingface
2026-11-20T21:49:06.232270pypi_downloads—61pypi
2026-11-20T21:49:06.232208discovered_conda——discovery
2026-11-20T21:49:06.232208discovered_cran——discovery
2026-11-20T21:49:06.232208discovered_doi——discovery
2026-11-20T21:49:06.232208discovered_hf—StanfordShahLab/gpt-base-512-clmbr,StanfordShahLab/gpt-base-1024-clmbr,StanfordShahLab/gpt-base-2048-clmbr,StanfordShahLab/gpt-base-4096-clmbr,StanfordShahLab/llama-base-512-clmbr,StanfordShahLab/llama-base-1024-clmbr,StanfordShahLab/llama-base-2048-clmbr,StanfordShahLab/llama-base-4096-clmbr,StanfordShahLab/mamba-tiny-1024-clmbr,StanfordShahLab/mamba-tiny-4096-clmbr,StanfordShahLab/mamba-tiny-8192-clmbr,StanfordShahLab/mamba-tiny-16384-clmbr,StanfordShahLab/hyena-large-1024-clmbr,StanfordShahLab/hyena-large-4096-clmbr,StanfordShahLab/hyena-large-8192-clmbr,StanfordShahLab/hyena-large-16384-clmbrdiscovery
2026-11-20T21:49:06.232208discovered_npm——discovery
2026-11-20T21:49:06.232208discovered_pypi—hf_ehrdiscovery
2026-11-20T21:49:04.499924has_ci—Falsegithub_api
2026-11-20T21:49:04.499924has_docs—Truegithub_api
2026-11-20T21:49:04.499924has_releases—Truegithub_api
2026-11-20T21:49:04.499924has_tests—Falsegithub_api
2026-11-20T21:49:04.499924repo_languages—Jupyter Notebook:91,Python:8,Shell:1github_api
2026-11-20T21:49:04.499850description—Training HuggingFace models on EHR datagithub_api
2026-11-20T21:49:04.499850license—Apache-2.0github_api
2026-11-20T21:49:04.499850repo_archived—Falsegithub_api
2026-11-20T21:49:04.499850repo_created—2023-10-05T07:36:06Zgithub_api
2026-11-20T21:49:04.499850repo_forks—10github_api
2026-11-20T21:49:04.499850repo_homepage—https://arxiv.org/abs/2412.16178github_api
2026-11-20T21:49:04.499850repo_last_commit—2025-11-02T04:11:51Zgithub_api
2026-11-20T21:49:04.499850repo_open_issues—6github_api
2026-11-20T21:49:04.499850repo_primary_language—Jupyter Notebookgithub_api
2026-11-20T21:49:04.499850repo_size_kb—21021github_api
2026-11-20T21:49:04.499850repo_stars—55github_api
2026-11-20T21:49:04.499850repo_topics—electronic-health-records,foundation-models,healthcare,machine-learninggithub_api