speakleash
/

Bielik-11B-v2.2-Instruct-Quanto-8bit

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

Bielik-11B-v2.2-Instruct-Quanto-8bit / generation_config.json

Remek's picture

Upload folder using huggingface_hub

1031cfb verified 3 months ago

115 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 32001,
	"transformers_version": "4.43.4"
	}