UMCU / CardioLM_encoder_base

huggingface.co
Total runs: 24
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: March 05 2025
fill-mask

Introduction of CardioLM_encoder_base

Model Details of CardioLM_encoder_base

Continued, on-premise, pre-training of MedRoBERTa.nl using about 50GB of open Dutch and translated English corpora.

Data statistics

Sources:

  • Dutch: medical guidelines (FMS, NHG)
  • Dutch: NtvG papers
  • English: Pubmed abstracts
  • English: PMC abstracts translated using DeepL
  • English: Apollo guidelines, papers and books
  • English: Meditron guidelines
  • English: MIMIC3
  • English: MIMIC CXR
  • English: MIMIC4

All translated (if not with DeepL) with performed with a combination of GeminiFlash 1.5/GPT4o mini, MariaNMT, NLLB200.

  • Number of tokens: 15B
  • Number of documents: 27M

Training

  • Effective batch size: 5120
  • Learning rate: 2e-4
  • Weight decay: 1e-3
  • Learning schedule: linear, with 5_000 warmup steps
  • Num epochs: ~3

Train perplexity: 3.0 Validation perplexity: 3.0

Acknowledgement

We were happy to be able to use the Google TPU research cloud for training the model.

Runs of UMCU CardioLM_encoder_base on huggingface.co

24
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About CardioLM_encoder_base huggingface.co Model

More CardioLM_encoder_base license Visit here:

https://choosealicense.com/licenses/gpl-3.0

CardioLM_encoder_base huggingface.co

CardioLM_encoder_base huggingface.co is an AI model on huggingface.co that provides CardioLM_encoder_base's model effect (), which can be used instantly with this UMCU CardioLM_encoder_base model. huggingface.co supports a free trial of the CardioLM_encoder_base model, and also provides paid use of the CardioLM_encoder_base. Support call CardioLM_encoder_base model through api, including Node.js, Python, http.

CardioLM_encoder_base huggingface.co Url

https://huggingface.co/UMCU/CardioLM_encoder_base

UMCU CardioLM_encoder_base online free

CardioLM_encoder_base huggingface.co is an online trial and call api platform, which integrates CardioLM_encoder_base's modeling effects, including api services, and provides a free online trial of CardioLM_encoder_base, you can try CardioLM_encoder_base online for free by clicking the link below.

UMCU CardioLM_encoder_base online free url in huggingface.co:

https://huggingface.co/UMCU/CardioLM_encoder_base

CardioLM_encoder_base install

CardioLM_encoder_base is an open source model from GitHub that offers a free installation service, and any user can find CardioLM_encoder_base on GitHub to install. At the same time, huggingface.co provides the effect of CardioLM_encoder_base install, users can directly use CardioLM_encoder_base installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

CardioLM_encoder_base install url in huggingface.co:

https://huggingface.co/UMCU/CardioLM_encoder_base

Url of CardioLM_encoder_base

CardioLM_encoder_base huggingface.co Url

Provider of CardioLM_encoder_base huggingface.co

UMCU
ORGANIZATIONS

Other API from UMCU

huggingface.co

Total runs: 4
Run Growth: 0
Growth Rate: 0.00%
Updated:October 03 2025