xihc-ucb
/

Meta-Llama-3-8B-vLLM-FP8-Block

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

Meta-Llama-3-8B-vLLM-FP8-Block / generation_config.json

xihc-ucb's picture

Upload LlamaForCausalLM

32c3500 verified 28 days ago

172 Bytes

	{
	"bos_token_id": 128000,
	"do_sample": true,
	"eos_token_id": 128001,
	"max_length": 4096,
	"temperature": 0.6,
	"top_p": 0.9,
	"transformers_version": "4.57.0"
	}