Sentence Similarity
Transformers
PyTorch
German
English
xlm-roberta
feature-extraction
semantic textual similarity
sts
semantic search
sentence similarity
paraphrasing
sentence-transformer
text-embeddings-inference
Instructions to use PM-AI/sts_paraphrase_xlm-roberta-base_de-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PM-AI/sts_paraphrase_xlm-roberta-base_de-en with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("PM-AI/sts_paraphrase_xlm-roberta-base_de-en") model = AutoModel.from_pretrained("PM-AI/sts_paraphrase_xlm-roberta-base_de-en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from PM-AI/sts_paraphrase_xlm-roberta-base_de-en: direct link, hf CLI and curl.
- Browser
- Download file 239 Bytes
-
https://huggingface.co/PM-AI/sts_paraphrase_xlm-roberta-base_de-en/resolve/accf7b600c2a7b7cf4ee1685e558c222982e2f1e/special_tokens_map.json
- Command line
-
hf download hf://PM-AI/sts_paraphrase_xlm-roberta-base_de-en@accf7b600c2a7b7cf4ee1685e558c222982e2f1e/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/PM-AI/sts_paraphrase_xlm-roberta-base_de-en/resolve/accf7b600c2a7b7cf4ee1685e558c222982e2f1e/special_tokens_map.json
239 Bytes
| {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}} |