HF1BitLLM
/

Llama3-8B-1.58-100B-tokens

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

Llama3-8B-1.58-100B-tokens / generation_config.json

medmekk's picture

medmekk HF staff

Upload LlamaForCausalLM

d58a59d verified 2 months ago

126 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128009,
	"transformers_version": "4.44.0.dev0"
	}