LeanQuant
/

Meta-Llama-3-8B-Instruct-nu-4bit

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

Meta-Llama-3-8B-Instruct-nu-4bit / generation_config.json

LeanQuant's picture

Upload LlamaForCausalLM

b83aba7 verified 12 months ago

history blame contribute delete

121 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128009,
	"transformers_version": "4.47.0"
	}