Voldis/marian-rus-bak

🏔️ DevLake: MarianMT (77M) for Russian-Bashkir

Current Model	Architecture	Focus
🔴 Large Model	NLLB-1.3B (QLoRA)	Best Quality (SOTA)
🟡 Medium Model	M2M-100 (418M)	Balanced
🟢 Small (This Model)	MarianMT (Full FT)	Fastest / CPU Friendly

Model Description

This is the Lightweight model from Team DevLake. Unlike the larger models, this is trained from scratch (transfer learning from English-Turkish) with a manually expanded vocabulary to support Bashkir Cyrillic characters.

It is designed for environments with limited resources (CPU deployment, mobile, etc.).

• Score: 43.15 CHRF++
• Parameters: 77M (Very fast)
• Caveat: May struggle with complex semantic nuances compared to NLLB.

⚠️ Important Usage Note

You must prepend the special token >>bak<< to the source sentence.

🚀 Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id = "Voldis/marian-rus-bak"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)

# Note the prefix!
text = ">>bak<< Добрый день, друзья!"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_length=128)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])

🛠️ Training Details

• Hardware: Trained on a single NVIDIA RTX 3080.

📚 Citation

@article{devlake2026loresmt,
  title={DevLake at LoResMT 2026: The Impact of Pre-training and Model Scale on Russian-Bashkir Low-Resource Translation},
  author={DevLake Team},
  year={2026}
}