Xlm Roberta De

🚀 airnicco8/xlm-roberta-de

This is a sentence-transformers model that maps sentences and paragraphs to a 768-dimensional dense vector space. It can be used for tasks such as clustering or semantic search. The model is trained on Ted talks transcripts filtered by the German language. The training setting is detailed here. It can be directly used for sentence similarity and can also be fine-tuned for NLI and text classification. Examples will be provided soon.

✨ Features

• Maps sentences and paragraphs to a 768-dimensional dense vector space.
• Can be used for clustering and semantic search.
• Applicable for sentence similarity tasks and can be fine - tuned for NLI and text classification.

📦 Installation

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

If you have sentence-transformers installed:

from sentence_transformers import SentenceTransformer
sentences = ["das ist eine glückliche Frau", "das ist ein glücklicher Mann", "das ist ein glücklicher Hund"]

model = SentenceTransformer('airnicco8/xlm-roberta-de')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ["das ist eine glückliche Frau", "das ist ein glücklicher Mann", "das ist ein glücklicher Hund"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('airnicco8/xlm-roberta-de')
model = AutoModel.from_pretrained('airnicco8/xlm-roberta-de')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

📚 Documentation

Evaluation Results

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training

The model was trained with the following parameters:

DataLoader: torch.utils.data.dataloader.DataLoader of length 3071 with parameters:

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss: sentence_transformers.losses.MSELoss.MSELoss

Parameters of the fit()-Method:

{
    "epochs": 10,
    "evaluation_steps": 1000,
    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "eps": 1e-06,
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 1000,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors