Helsinki-NLP
/

opus-mt-sv-tum

text2text-generation

Inference Endpoints

Model card Files Files and versions Community

opus-mt-sv-tum / generation_config.json

joaogante's picture

joaogante HF staff

set `renormalize_logits=True` for better performance (see `transformers` issue #4290)

5c844f5 about 1 year ago

history blame contribute delete

222 Bytes

	{
	"bos_token_id": 0,
	"decoder_start_token_id": 61278,
	"eos_token_id": 0,
	"forced_eos_token_id": 0,
	"num_beams": 6,
	"pad_token_id": 61278,
	"renormalize_logits": true,
	"transformers_version": "4.32.0.dev0"
	}