ModernCamemBERT-bio-v2-base is a French biomedical encoder for document-level tasks. It is obtained by continuing the pretraining of
ModernCamemBERT-bio-base
with an OntoBook phase, with an 8,192-token context window. On our French biomedical document benchmark it reaches 70.0 micro-F1 at 150M parameters. A larger version is available as
ModernCamemBERT-bio-v2-large
.
Authors
Rian Touchent and Eric de la Clergerie
Sorbonne Université, Inria Paris
Overview
ModernCamemBERT-bio is already adapted to French biomedical text through a CLM detour. The v2 variant adds a second continued-pretraining phase that we call OntoBook. Instead of plain masked language modeling, we train on ontology-grounded synthetic textbooks built from CIM-10, CCAM and ATC ontology walks, mixed with clinical text. The aim is to inject structured coding knowledge without adding a task-specific head. This is the base-size document specialist.
from transformers import AutoTokenizer, AutoModelForMaskedLM
model_id = "rntc/ModernCamemBERT-bio-v2-base"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForMaskedLM.from_pretrained(model_id)
text = "Le patient présente une [MASK] aiguë du myocarde."
inputs = tokenizer(text, return_tensors="pt")
logits = model(**inputs).logits
i = inputs["input_ids"][0].tolist().index(tokenizer.mask_token_id)
print(tokenizer.decode(logits[0, i].argmax(-1)))
Evaluation
Per-task results on the document core of our French biomedical benchmark, scored with micro-F1 and averaged over nine seeds.
Model
FrACCO-30
FrACCO-100
CANTEMIST
MORFITT
MedDialog-FR
Avg
ModernCamemBERT-bio-v2-large
82.0
67.8
74.6
74.3
65.2
72.8
ModernCamemBERT-bio-v2-base
78.0
63.7
70.9
73.5
63.7
70.0
ModernCamemBERT-bio-base
74.2
61.1
71.2
72.9
63.7
68.6
DoctoModernBERT
74.0
58.3
69.3
73.9
64.7
68.0
DrBERT
54.2
39.6
41.2
71.0
64.1
54.0
DoctoBERT
51.6
34.7
36.2
73.5
62.1
51.6
CamemBERT-bio
44.0
22.3
17.7
70.9
45.8
40.1
At base size, ModernCamemBERT-bio-v2-base leads the average and scores 1.4 points above its ModernCamemBERT-bio-base starting point. ModernCamemBERT-bio-v2-large scores 2.8 points higher at 350M parameters.
Environmental impact
The OntoBook phase reported here ran for about 1.3 GPU-hours on a single H100, on the Jean Zay cluster (GENCI-IDRIS) in France. We estimate roughly 0.04 kg CO2eq for this phase. This figure covers the continued-pretraining step only and does not include the pretraining of the base model.
License
MIT
Citation
@inproceedings{touchent:hal-05697506,
TITLE = {{OntoBook: Ontology-Grounded Synthetic Textbooks for Medical Encoder Pretraining}},
AUTHOR = {Touchent, Rian and de la Clergerie, {\'E}ric},
URL = {https://hal.science/hal-05697506},
BOOKTITLE = {{Proceedings of Knowledge Graphs and Large Language Models Workshop}},
ADDRESS = {Palma de Mallorca, Spain},
YEAR = {2026},
MONTH = May,
PDF = {https://hal.science/hal-05697506v1/file/main.pdf},
HAL_ID = {hal-05697506},
HAL_VERSION = {v1},
}
@misc{touchent2026causallanguagemodelingdetour,
title={A Causal Language Modeling Detour Improves Encoder Continued Pretraining},
author={Rian Touchent and Eric de la Clergerie},
year={2026},
eprint={2605.12438},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2605.12438},
}
Runs of almanach ModernCamemBERT-bio-v2-base on huggingface.co
19
Total runs
0
24-hour runs
2
3-day runs
5
7-day runs
-68
30-day runs
More Information About ModernCamemBERT-bio-v2-base huggingface.co Model
More ModernCamemBERT-bio-v2-base license Visit here:
ModernCamemBERT-bio-v2-base huggingface.co is an AI model on huggingface.co that provides ModernCamemBERT-bio-v2-base's model effect (), which can be used instantly with this almanach ModernCamemBERT-bio-v2-base model. huggingface.co supports a free trial of the ModernCamemBERT-bio-v2-base model, and also provides paid use of the ModernCamemBERT-bio-v2-base. Support call ModernCamemBERT-bio-v2-base model through api, including Node.js, Python, http.
ModernCamemBERT-bio-v2-base huggingface.co is an online trial and call api platform, which integrates ModernCamemBERT-bio-v2-base's modeling effects, including api services, and provides a free online trial of ModernCamemBERT-bio-v2-base, you can try ModernCamemBERT-bio-v2-base online for free by clicking the link below.
almanach ModernCamemBERT-bio-v2-base online free url in huggingface.co:
ModernCamemBERT-bio-v2-base is an open source model from GitHub that offers a free installation service, and any user can find ModernCamemBERT-bio-v2-base on GitHub to install. At the same time, huggingface.co provides the effect of ModernCamemBERT-bio-v2-base install, users can directly use ModernCamemBERT-bio-v2-base installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
ModernCamemBERT-bio-v2-base install url in huggingface.co: