---
base_model: openbmb/MiniCPM5-1B
library_name: transformers
model_name: ZygAI-OSS-Translate-Lithuanian
tags:
- translation
- lithuanian
- english-to-lithuanian
- trl
- sft
- peft
- lora
- zygai
language:
- en
- lt
license: apache-2.0
datasets:
- Helsinki-NLP/opus-100
- ZygAI/zygai_lt
---

# ZygAI OSS Translator — English → Lithuanian

<div align="center">
<img src="https://huggingface.co/ZygAI/ZygAI-OSS-Translate-Lithuanian/resolve/main/logo.png" width="200"/>
</div>

ZygAI OSS Translate Lithuanian is a fine-tuned version of [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B), specialized for English to Lithuanian translation. It is part of the [ZygAI](https://zygai.app) open source initiative to bring AI tools to the Lithuanian language.

> 🇱🇹 First open-source Lithuanian translation model based on MiniCPM5 architecture.

<img src="https://huggingface.co/ZygAI/ZygAI-OSS-Translate-Lithuanian/resolve/main/zygai-lithuanian.png" width="600"/>

## Demo

Try it live: [ZygAI Translate Lithuanian DEMO](https://huggingface.co/spaces/ZygAI/ZygAI-Translate-Lithuanian-DEMO)

## Run Locally

```bash
# Clone repository
git clone https://huggingface.co/spaces/ZygAI/ZygAI-Translate-Lithuanian-DEMO
cd ZygAI-Translate-Lithuanian-DEMO

# Create and activate Python environment
python -m venv env
source env/bin/activate

# Install dependencies and run
pip install -r requirements.txt
python app.py
```

## Quick Start

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base_model = "openbmb/MiniCPM5-1B"
lora_model = "ZygAI/ZygAI-OSS-Translate-Lithuanian"

tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model, dtype=torch.float16)
model = PeftModel.from_pretrained(model, lora_model)
model.eval()

def translate(text):
    prompt = f"### Instruction:\n{text}\n### Response:\n"
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(**inputs, max_new_tokens=128)
    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return result.split("### Response:\n")[-1]

print(translate("Hello, how are you?"))
# → Labas pasaulis
print(translate("How are you?"))
# → O kaip jūs?
```

## Training Details

| Parameter | Value |
|---|---|
| Base model | openbmb/MiniCPM5-1B |
| Dataset | Helsinki-NLP/opus-100 (en-lt) |
| Training samples | 50,000 |
| Method | SFT + LoRA (PEFT) |
| LoRA rank | 16 |
| LoRA alpha | 32 |
| Epochs | 3 |
| Batch size | 4 |
| Max sequence length | 256 |
| Hardware | NVIDIA A100 SXM |
| Framework | TRL + Transformers |

## Limitations

Translation quality is functional but not perfect — this is an open-source community model, not a production translation service. Future versions will include larger datasets, better evaluation metrics, and improved inference quality.

## About ZygAI

ZygAI is a Lithuanian AI platform developed by [ZygMediaGroup](https://zygmediagroup.com). This model is part of ZygAI's open source effort to develop Lithuanian language AI tools accessible to everyone.

## License

Apache 2.0

## Citation

```bibtex
@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}
```