instilux/ltz-e1-mini

LTZ E1 (mini)

A ModernBERT-based masked language model pretrained on Luxembourgish, following the Ettin recipe (see here: https://huggingface.co/jhu-clsp/ettin-encoder-68m)

Model Details

• Architecture: ModernBERT (encoder)
• Size: mini
• Vocabulary: 50,368 tokens (BPE, GPTNeoXTokenizerFast)
• Context length: 1,024 tokens
• Language: Luxembourgish (lb/ltz)
• License: CC BY-SA 4.0

Usage

Requires transformers>=4.48.0.

from transformers import AutoModelForMaskedLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("instilux/ltz-e1-mini")
model = AutoModelForMaskedLM.from_pretrained("instilux/ltz-e1-mini")

inputs = tokenizer("Wéi spéit [MASK] et?", return_tensors="pt")
mask_pos = (inputs["input_ids"] == tokenizer.mask_token_id).nonzero(as_tuple=True)[1]

with torch.no_grad():
    outputs = model(**inputs)

top_tokens = outputs.logits[0, mask_pos].topk(5)
for token_id, score in zip(top_tokens.indices[0], top_tokens.values[0]):
    token = tokenizer.decode(token_id)
    print(f"{token:15s} {score:.3f}")

Tokenizer Notes

The tokenizer is BPE-based (GPTNeoXTokenizerFast) with BERT-style special tokens ([CLS], [SEP], [MASK], [PAD]). A [CLS] token is prepended automatically (add_bos_token: true).

Citation

A paper describing this model will be published soon. In the meantime, please cite this repository if you use this model in your work.