capston-team-5
/

finma-7b-4bit-quantized

4-bit precision

Model card Files Files and versions

finma-7b-4bit-quantized / generation_config.json

Esyur's picture

Upload 4bit quantized finma-7b model

81af137 verified 11 months ago

history blame contribute delete

132 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 0,
	"eos_token_id": 1,
	"pad_token_id": 0,
	"transformers_version": "4.51.3"
	}