nm-testing
/

Llama-2-7b-hf-weight-input-quant-compressed

8-bit precision

compressed-tensors

Model card Files Files and versions

Llama-2-7b-hf-weight-input-quant-compressed / generation_config.json

kylesayrs's picture

Upload folder using huggingface_hub

ffebb09 verified 10 months ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.52.3"
	}