Downloads · 30 days
12
21% of all-time downloads
pguerrero-igutierrez/Latxa-Qwen3-8B-Clinical-v2-ca-eu
Latxa-Qwen3-8B-Clinical-v2-ca-eu is a text generation model from pguerrero-igutierrez. Use it when you need the model to write or continue text. It is set up for peft.
Latxa-Qwen3-8B-Clinical-v2-ca-eu is a LoRA adapter for Catalan-to-Basque clinical translation. It continues fine-tuning from the project general-domain checkpoint and targets the clinical CA-EU direction.
Downloads · 30 days
12
21% of all-time downloads
All-time downloads
57
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.pt699 MB · 55%
From the Hugging Face model README
Latxa-Qwen3-8B-Clinical-v2-ca-eu is a LoRA adapter for Catalan-to-Basque clinical translation. It continues fine-tuning from the project general-domain checkpoint and targets the clinical CA->EU direction.
HiTZ/Latxa-Qwen3-VL-8B-Instructca), Basque (eu)ca->eu onlyHiTZ/Latxa-Qwen3-VL-8B-Instructpguerrero-igutierrez/Latxa-Qwen3-8B-General-eu-capguerrero-igutierrez/Latxa-Qwen3-8B-Clinical-v2-ca-eupguerrero-igutierrez/mt-domain-adaptation-ca-euThis model is intended for research on continued domain adaptation for low-resource clinical Catalan-Basque translation.
Supported prompting direction:
ca->eu: Tradueix aquest text clínic del català al basc:\n\n{source}eu->ca)The adapter uses the same back-translated clinical corpus as clinicalv1:
backtranslated-corpus/eu-clinical_backtranslated.jsonSynthetic Catalan is used as source and original Basque as target.
q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj5e-5Results on the clinical held-out test set:
| Direction | chrF++ | BLEU | TER | COMET |
|---|---|---|---|---|
ca->eu | 38.73 | 18.50 | 104.64 | 75.02 |
In the project experiments, this continued-adaptation model performed slightly below the direct clinical SFT model (clinicalv1) across the reported clinical metrics.
ca->euimport 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-Clinical-v2-ca-eu"
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 = "Tradueix aquest text clínic del català al basc:\n\nEl pacient presenta febre alta."
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))
@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}
}
[email protected][email protected]