T-Systems-onsite
/

cross-en-de-roberta-sentence-transformer

Feature Extraction

sentence_embedding

xlm-r-distilroberta-base-paraphrase-v1

text-embeddings-inference

Inference Endpoints

Model card Files Files and versions Community

cross-en-de-roberta-sentence-transformer / tokenizer_config.json

Jimmy Neitzert

fix: add missing files from base-model and set clean_up_tokenization_spaces = True to fix the warnings

1c87fa1 5 months ago

237 Bytes

	{
	"model_max_length": 512,
	"special_tokens_map_file": "input_models/johngiorgi-declutr-small-all-paraphrase-multilingual/0_Transformer/special_tokens_map.json",
	"full_tokenizer_file": null,
	"clean_up_tokenization_spaces": true
	}