Model details

• Developed by: Paula Guerrero and Iker Gutierrez
• Affiliation: University of the Basque Country (EHU)
• Model type: LoRA adapter for HiTZ/Latxa-Qwen3-VL-8B-Instruct
• Languages: Catalan (ca), Basque (eu)
• Domain: General
• Base model: HiTZ/Latxa-Qwen3-VL-8B-Instruct
• Repository: pguerrero-igutierrez/Latxa-Qwen3-8B-General-eu-ca
• Collection: pguerrero-igutierrez/mt-domain-adaptation-ca-eu

Sources

• Hugging Face repository: https://huggingface.co/pguerrero-igutierrez/Latxa-Qwen3-8B-General-eu-ca
• Hugging Face collection: https://huggingface.co/collections/pguerrero-igutierrez/mt-domain-adaptation-ca-eu
• Project repository: https://github.com/pguerrero-igutierrez/MT-domain-adaptation
• Paper source: https://github.com/pguerrero-igutierrez/MT-domain-adaptation/tree/main/paper

Intended use

This model is intended as the general-domain CA-EU baseline of the project and as a warm-start checkpoint for continued literary and clinical adaptation.

Supported prompting directions:

• eu->ca: Itzuli testu hau euskaratik katalanera:\n\n{source}
• ca->eu: Tradueix aquest text del català al basc:\n\n{source}

Out-of-scope use

• High-stakes use without human review
• Specialized clinical translation
• Professional literary translation without post-editing
• Translation outside the Catalan-Basque pair

Training data

The adapter was trained on a 50k-pair sample from projecte-aina/CA-EU_Parallel_Corpus, converted into bidirectional instruction examples for both translation directions.

Training procedure

• LoRA rank: 16
• LoRA alpha: 32
• LoRA dropout: 0.05
• Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
• Quantization: 4-bit NF4
• Max sequence length: 768
• Epochs: 3
• Batch size: 4
• Gradient accumulation: 8
• Learning rate: 5e-5
• Scheduler: cosine
• Warmup ratio: 0.05
• Seed: 42
• Checkpoint selection: best validation BLEU

Evaluation

Results on the general-domain held-out test set:

This model substantially improved over the base zero-shot baseline and served as the continued-fine-tuning starting point for literaryv2 and clinicalv2.

Limitations

• General-domain data does not capture literary style or clinical terminology well enough for strong in-domain specialization
• Performance in CA->EU remains harder than EU->CA under strict overlap metrics
• Results are specific to the Latxa-Qwen3-VL-8B-Instruct base model and LoRA setup used in the project

Usage

python
Copy code
import torch
from peft import PeftModel
from transformers import AutoTokenizer, Qwen3VLForConditionalGeneration

base_id = "HiTZ/Latxa-Qwen3-VL-8B-Instruct"
adapter_id = "pguerrero-igutierrez/Latxa-Qwen3-8B-General-eu-ca"

tokenizer = AutoTokenizer.from_pretrained(base_id, trust_remote_code=True)
base_model = Qwen3VLForConditionalGeneration.from_pretrained(
    base_id,
    device_map="auto",
    torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(base_model, adapter_id)

prompt = "Itzuli testu hau euskaratik katalanera:\n\nKaixo mundua."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Citation

bibtex
Copy code
@misc{guerrero-gutierrez-2026-caeu-mt,
  title        = {Domain Adaptation for Catalan-Basque Machine Translation via Synthetic Data and Continued Fine-Tuning},
  author       = {Guerrero, Paula and Gutierrez, Iker},
  year         = {2026},
  note         = {Unpublished manuscript}
}

Contact

• Paula Guerrero: pguerrero005@ikasle.ehu.eus
• Iker Gutierrez: igutierrez134@ikasle.ehu.eus