neuralmagic
/

Llama-3.2-3B-quantized.w8a8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Llama-3.2-3B-quantized.w8a8 / generation_config.json

alexmarques's picture

Upload folder using huggingface_hub

4d12d86 verified about 1 month ago

history blame contribute delete

121 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128001,
	"transformers_version": "4.44.1"
	}