Alpha
All entriesContact
Model

MeditronFO

Publisher
LiGHT laboratory (Laboratory for Intelligent Global Health & Humanitarian Response Technologies), EPFL, School of Computer and Communication Sciences (CH)
Family
Meditron
Openness
open_weights_recipe
Licence
Apache License 2.0 (declared in model card metadata and card header; no LICENSE file in the weight repositories)
Context
65,536 (config max_position_embeddings; fine-tuned on 8,192-token packed sequences)

Ownership is partial. The release is an inspectable medical fine-tune that can be run, adapted and audited on the deployer's own hardware, and the pipeline behind it is public. It is not a clinically usable or clearly licensed product: the publisher bars patient decisions, there is no LICENSE file, the corpus licence is stated two ways, and safety evaluation is thin. Ownership moves to substantial if EPFL ships a LICENSE file and reconciles the corpus licence, and a deployer adds an independent clinical safety evaluation.

Do you really own it?
Partial
none·limited·partial·substantial·full
Analytical input: AOI D · 51.2/100
The four ownership factors

Floor-weighted, not averaged. Reliability is weak, and the weakest factor sets the ceiling, so the verdict stays partial however strong the rest.

1

Use and modify freelyCan you run, modify and adapt it with no gate and no field-of-use trap?

Moderate

Apache-2.0 is declared and the weights are ungated and fine-tunable. The declaration sits in metadata only, with no LICENSE file, a paper that calls the corpus research-use, flagged source-dataset terms and a base acceptable-use policy of unclear reach, so the chain of title is unresolved.

How this scores (AOI sub-dimensions)
Openness4/5how much is released - weights, data, code, licence - and how freelyOpen weights plus recipe: BF16 safetensors, a released 533,888-example corpus with row-level source fields, public data-generation, decontamination, training (Axolotl configs) and evaluation code under Apache-2.0 on GitHub, and a fully open base (Apertus).
Legal2/5how permissive and clean the licence is for real commercial useA permissive licence is declared (Apache-2.0) with material caveats a deployer must resolve.
2

TransparencyDo you know what it is: weights, training, behaviour, and legible terms?

Strong

Weights, a 533,888-row corpus with source fields and the generation, training and evaluation code are public on a fully open base (open_weights_recipe), with the unreleased intermediates and MOOVE vignettes listed in the README.

How this scores (AOI sub-dimensions)
Provenance2/5how well we can trace and verify what went into the modelSafetensors only with an LFS sha256 per shard, and a well-documented training lineage.
Governance3/5how accountable and well-documented the publisher isAn identifiable university laboratory (EPFL LiGHT) with a named team, Swiss AI Initiative and CSCS funding, a contact address, a community tab and commits through 2026-11-17.
3

ReliabilityIs it reliable and good enough for the job?

Weak

Safety is 2: no safety tuning, publisher-only low-agreement safety judging and no guard or red-team, and the publisher says not to use it for patient decisions, so it is not safe to deploy as presented.

How this scores (AOI sub-dimensions)
Operational3/5how practical it is to run, serve and maintain in productionStandard transformers architecture class supported since transformers 4.56 per the base card, BF16 safetensors, a chat template and recommended sampling settings in generation_config, and community GGUF and MLX conversions for both sizes.
Safety2/5whether misuse risks are evaluated and guardrails are providedThe models are supervised fine-tunes for medical accuracy and not safety tuning.
4

Doesn't extract your dataDoes running it keep your knowledge and data yours?

Strong

Self-hosted BF16 safetensors run on the deployer's own hardware with no telemetry or licence clawback in the declared Apache-2.0 grant.

How this scores
Not a scored AOI dimension. For a self-hosted model, data-control is a structural property of running the weights yourself, strong by default unless the model phones home or the licence claws back rights. For a hosted API this factor is the retention + train-on-inputs + residency read, scored from the binding terms.

How the AOI score is computed

The seven dimensions above, each scored 0 to 5, weighted and summed to the 0 to 100 headline. The score is the analytical input behind the ownership verdict, not the verdict itself.

DimensionScoreWeightPoints
Openness4/50.1814.4
Provenance2/50.166.4
Legal2/50.166.4
Safety2/50.166.4
Performance2/50.145.6
Operational3/50.127.2
Governance3/50.084.8
HeadlineD · 51.2/100
Dossier coverageAssess 87%Implement 73%Use 61%Support 39%How complete our four-domain documentation is, a measure of our coverage, not of the model. Each domain links to its page.

Sources

Every rating traces to a primary document. Read means the text was verified; unverified means it is known to exist but has not yet been read.

DocumentWhat it grounds
Model cardread2026-11-19
The Apertus-70B-MeditronFO model card declares licence tag apache-2.0 and an Apache 2.0 link in the header.
Model cardread2026-11-19
The Apertus-8B-MeditronFO model card (partial extracts) has the same template and licence tag, base swiss-ai/Apertus-8B-Instruct-2509, a five-benchmark average of 48.26 against 42.39 for the base, and preference over the base in 74.2 percent of AutoMOOVE comparisons.
Documentationread2026-11-19
Hugging Face records show both repositories are ungated, safetensors only (30 shards for 70B, 4 for 8B, each with an LFS sha256) and without a LICENSE file (raw LICENSE is HTTP 404).
Licenceread2026-11-19
The GitHub code repository EPFLiGHT/FullyOpenMeditron carries an Apache License 2.0 LICENSE file added 2026-08-03.
Documentationread2026-11-19
The project page states the MeditronFO models are not medical devices, have not been tested in clinical practice and must not be used to make decisions about a patient.
Documentationread2026-11-19
The GitHub README says the repository holds the data pipeline, training configs and evaluation to reproduce the paper.
Documentationread2026-11-19
The dataset card gives an Apache-2.0 tag, 533,888 rows in four components and every answer by gpt-oss-120b.
Technical_reportread2026-11-19
arXiv 2605.16215 v2 (29 May 2026) says the corpus is released under a research-use licence and that assets are restricted to research purposes.
Model cardread2026-11-19
The Apertus-70B-Instruct-2509 base card (the 8B card is identical apart from the name) declares licence tag apache-2.0.
Model cardread2026-11-19
gpt-oss-120b, the teacher that wrote every training answer, is Apache-2.0 with a one-sentence usage policy requiring compliance with applicable law.
Vendor announcementread2026-11-19
The EPFL AI Center news item of 17 June 2026 describes MeditronFO as the first fully open framework for medical LLMs and says every stage of development is publicly available.
Vendor announcementread2026-11-19
The Meditron website gives a family history from Meditron 1 (2023) to MeditronFO (2026), a contact address for the lab, and a chat disclaimer saying it is a research model, not a doctor, that can be wrong.
Documentationread2026-11-19
The Hugging Face listing of the EPFLiGHT organisation shows five MeditronFO checkpoints with the licence tag apache-2.0 (Apertus 70B and 8B, OLMo-2-32B, EuroLLM-22B and 9B).
Third-party analysisread2026-11-19
A Hugging Face search for MeditronFO lists community GGUF and i1-GGUF conversions of both Apertus sizes by mradermacher, an MLX conversion of the 8B by loleg and Q4 and Q5 GGUF of the 8B by BrazosDeDios.
Documentationunverified2026-11-19
The Apertus card links an EU AI Act public summary and a Code of Practice document for the base model.