---
license: mit
datasets:
- Thermostatic/Axolotl-Spanish-Nahuatl-ShareGPT-Filtered-Splits
language:
- es
- nah
tags:
- Translation
- Gemma 3
- Spanish
- Nahuatl
- Machine translation
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c8b32f36c11430f3149da8/VWFlg-T1WSCFsynhw8uzr.png)

# Model Card for NeuralTranslate

<!-- Provide a quick summary of what the model is/does. -->

THIS MODEL USES GEMMA 3 TEMPLATE.

This is the first official release of NeuralTranslate 27b Machine Translation: Spanish to Nahuatl. The base model is Gemma 3 27b Instruct after being trained in the Axolotl Spanish-Nahuatl Dataset for 10 epochs.

You can donate towards this project at my ko-fi! https://ko-fi.com/irvingernesto


## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Developed by:** Irving Ernesto
- **Funded by:** Irving Ernesto
- **Model type:** Large Language Model
- **Language(s) (NLP):** Spanish & Náhuatl
- **License:** MIT
- **Finetuned from model [optional]:** Gemma 3 27b

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/Sekinal/neuraltranslate-nahuatl
- **Demo:** https://huggingface.co/spaces/Thermostatic/neuraltranslate-27b-mt-nah-es

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

Translating between any other two pair of languages. E.g., trying to use the model to translate Náhuatl to English won't work. Even using the model to translate from Spanish to Náhuatl is not reliable.

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Use the recommended settings for the Gemma 3 model for inference: `temperature = 1.0, top_p = 0.95, top_k = 64`

## How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]