huggingface--transformers/docs/source/en/model_doc/eurobert.md

This model was published in HF papers on 2025-03-07 and contributed to Hugging Face Transformers on 2026-03-04.

EuroBERT

Overview

EuroBERT is a multilingual encoder model based on a refreshed transformer architecture, akin to Llama but with bidirectional attention. It supports a mixture of European and widely spoken languages, with sequences of up to 8192 tokens.

You can find all the original EuroBERT checkpoints under the EuroBERT collection, or read more about the release in the EuroBERT blogpost.

The example below demonstrates how to predict the <|mask|> token with [Pipeline], [AutoModel], and from the command line.

from transformers import pipeline


pipeline = pipeline(
    task="fill-mask",
    model="EuroBERT/EuroBERT-210m",
    device=0
)
pipeline("Plants create <|mask|> through a process known as photosynthesis.")

import torch

from transformers import AutoModelForMaskedLM, AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained(
    "EuroBERT/EuroBERT-210m",
)
model = AutoModelForMaskedLM.from_pretrained(
    "EuroBERT/EuroBERT-210m",
    device_map="auto",
    attn_implementation="sdpa"
)
inputs = tokenizer("Plants create <|mask|> through a process known as photosynthesis.", return_tensors="pt").to(model.device)

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

masked_index = torch.where(inputs['input_ids'] == tokenizer.mask_token_id)[1]
predicted_token_id = predictions[0, masked_index].argmax(dim=-1)
predicted_token = tokenizer.decode(predicted_token_id)

print(f"The predicted token is: {predicted_token}")

EuroBertConfig

autodoc EuroBertConfig

EuroBertModel

autodoc EuroBertModel - forward

EuroBertForMaskedLM

autodoc EuroBertForMaskedLM - forward

EuroBertForSequenceClassification

autodoc EuroBertForSequenceClassification - forward

EuroBertForTokenClassification

autodoc EuroBertForTokenClassification - forward