feelconstantfear
/

Llama-3.2-1B-QPTQ

4-bit precision

Model card Files Files and versions Community

Llama-3.2-1B-QPTQ / generation_config.json

feelconstantfear's picture

feelconstantfear

Upload LlamaForCausalLM

e8c21d1 verified about 2 months ago

121 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128001,
	"transformers_version": "4.44.0"
	}