# Rosa Rodriguez-Sánchez: Open-Weight Models and Datasets
Source: https://savrn.com/model-publishers/rosadecsai
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model

### [led-large-16384-BASE3ep-ASPRPreACE3ep](https://savrn.com/models/led-large-16384-base3ep-asprpreace3ep)

[Rosa Rodriguez-Sánchez](https://savrn.com/model-publishers/rosadecsai)

This model is a fine-tuned version of rosadecsai/led-large-16384-BASE3ep on the None dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 16 - lrschedulertype: linear - numepochs: 3 - mixedprecisiontraining: Native AMP - Transformers 4.48.3 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.21.4

Open weights apache-2.0 460M parameters transformers

[View model](https://savrn.com/models/led-large-16384-base3ep-asprpreace3ep)

## Explore More

- [All model publishers](https://savrn.com/model-publishers)
- [The model directory](https://savrn.com/models)
- [The dataset directory](https://savrn.com/datasets)

## Source

- Listed from their public repositories, read 2026-09-29.
- [Hugging Face profile](https://huggingface.co/rosadecsai)
- [How the hub is built](https://savrn.com/model-hub/methodology)