Family of Time Series Language Models (TSLMs) from Stanford Biodesign for Digital Health (BDHG) that integrate time series as a native modality into pretrained LLMs, enabling natural-language prompting and reasoning over multivariate clinical time series of any length. Supports 12-lead ECG question answering, EEG sleep stage classification, and human activity recognition from accelerometry. Two architecture variants: Soft Prompt (SP) and Flamingo. Available as Llama 3.2 (1B/3B) and Gemma 3 fine-tuned variants on HuggingFace. Accepted at ICML 2026 (Deep Learning / LLM main track). 1,200+ GitHub stars. Real-world adoption: Seattle Children's Hospital adopted OpenTSLM for pediatric ECG analysis toward a cardiac ICU clinical decision-support foundation model. Consortium includes researchers from major frontier AI labs and universities. MIT, Python.
Adopt — last commit ~4 months ago; 1273 stars (strong community); permissive licence (MIT).
Derived deterministically by the MACH scorer from the signals below — not written prose.
Maintained — last commit ~4 mo ago; has tests, CI
★ 1,273 stars · 129 forks · 19 open issues
Python 99% Shell 1%
Every value records the source it was harvested from.
| Field | Value | Source |
|---|---|---|
| citations | 52 | openalex |
| description | OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data | github_api |
| discovered_conda | not_found | discovery |
| discovered_cran | not_found | discovery |
| discovered_doi | 10.48550/arXiv.2510.02410,10.48550/arXiv.2510.02410-blue | discovery |
| discovered_hf | meta-llama/Llama-3.2-1B,google/gemma-3-270m | discovery |
| discovered_npm | not_found | discovery |
| discovered_pypi | opentslm | discovery |
| has CI | True | github_api |
| has docs | True | github_api |
| has releases | False | github_api |
| has tests | True | github_api |
| HuggingFace downloads (monthly) | not_found | huggingface |
| judgement | Adopt | mach_scorer |
| judgement reason | Adopt — last commit ~4 months ago; 1273 stars (strong community); permissive licence (MIT). | mach_scorer |
| license | MIT | github_api |
| openalex_id | https://openalex.org/W7084138770 | openalex |
| openalex_type | preprint | openalex |
| openalex_venue | arXiv (Cornell University) | openalex |
| publication_year | 2025 | openalex |
| PyPI downloads (monthly) | 92 | pypi |
| archived | False | github_api |
| repository created | 2025-05-14T22:31:33Z | github_api |
| GitHub forks | 129 | github_api |
| repo health | Maintained | mach_health |
| repo health reason | last commit ~4 mo ago; has tests, CI | mach_health |
| homepage | https://www.opentslm.com | github_api |
| languages | Python:99,Shell:1 | github_api |
| last commit | 2026-07-21T05:24:22Z | github_api |
| open issues | 19 | github_api |
| primary language | Python | github_api |
| repo_size_kb | 8494 | github_api |
| GitHub stars | 1273 | github_api |
| topics | ok | github_api |
Recorded deviations — when a harvested value changed between runs.
| When | Field | Was | Now | Source |
|---|---|---|---|---|
| 2026-11-20T21:53:47.066213 | repo_health | — | Maintained | mach_health |
| 2026-11-20T21:53:47.066213 | repo_health_reason | — | last commit ~4 mo ago; has tests, CI | mach_health |
| 2026-11-20T21:53:47.066144 | judgement | — | Adopt | mach_scorer |
| 2026-11-20T21:53:47.066144 | judgement_reason | — | Adopt — last commit ~4 months ago; 1273 stars (strong community); permissive licence (MIT). | mach_scorer |
| 2026-11-20T21:47:05.483405 | hf_downloads | — | — | huggingface |
| 2026-11-20T21:47:05.425862 | pypi_downloads | — | 92 | pypi |
| 2026-11-20T21:47:04.890597 | citations | — | 52 | openalex |
| 2026-11-20T21:47:04.890597 | openalex_id | — | https://openalex.org/W7084138770 | openalex |
| 2026-11-20T21:47:04.890597 | openalex_type | — | preprint | openalex |
| 2026-11-20T21:47:04.890597 | openalex_venue | — | arXiv (Cornell University) | openalex |
| 2026-11-20T21:47:04.890597 | publication_year | — | 2025 | openalex |
| 2026-11-20T21:47:04.890545 | discovered_conda | — | — | discovery |
| 2026-11-20T21:47:04.890545 | discovered_cran | — | — | discovery |
| 2026-11-20T21:47:04.890545 | discovered_doi | — | 10.48550/arXiv.2510.02410,10.48550/arXiv.2510.02410-blue | discovery |
| 2026-11-20T21:47:04.890545 | discovered_hf | — | meta-llama/Llama-3.2-1B,google/gemma-3-270m | discovery |
| 2026-11-20T21:47:04.890545 | discovered_npm | — | — | discovery |
| 2026-11-20T21:47:04.890545 | discovered_pypi | — | opentslm | discovery |
| 2026-11-20T21:47:02.674219 | has_ci | — | True | github_api |
| 2026-11-20T21:47:02.674219 | has_docs | — | True | github_api |
| 2026-11-20T21:47:02.674219 | has_releases | — | False | github_api |
| 2026-11-20T21:47:02.674219 | has_tests | — | True | github_api |
| 2026-11-20T21:47:02.674219 | repo_languages | — | Python:99,Shell:1 | github_api |
| 2026-11-20T21:47:02.674145 | description | — | OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data | github_api |
| 2026-11-20T21:47:02.674145 | license | — | MIT | github_api |
| 2026-11-20T21:47:02.674145 | repo_archived | — | False | github_api |
| 2026-11-20T21:47:02.674145 | repo_created | — | 2025-05-14T22:31:33Z | github_api |
| 2026-11-20T21:47:02.674145 | repo_forks | — | 129 | github_api |
| 2026-11-20T21:47:02.674145 | repo_homepage | — | https://www.opentslm.com | github_api |
| 2026-11-20T21:47:02.674145 | repo_last_commit | — | 2026-07-21T05:24:22Z | github_api |
| 2026-11-20T21:47:02.674145 | repo_open_issues | — | 19 | github_api |
| 2026-11-20T21:47:02.674145 | repo_primary_language | — | Python | github_api |
| 2026-11-20T21:47:02.674145 | repo_size_kb | — | 8494 | github_api |
| 2026-11-20T21:47:02.674145 | repo_stars | — | 1273 | github_api |
| 2026-11-20T21:47:02.674145 | repo_topics | — | — | github_api |