hivata
/

llama3-llava-next-8b-hf-AWQ

4-bit precision

Model card Files Files and versions Community

llama3-llava-next-8b-hf-AWQ / generation_config.json

LHC88's picture

Upload folder using huggingface_hub

55a1163 verified 9 months ago

142 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"do_sample": true,
	"eos_token_id": 128009,
	"transformers_version": "4.44.0"
	}