mgoin
/

Meta-Llama-3-70B-Instruct-Marlin

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Meta-Llama-3-70B-Instruct-Marlin / generation_config.json

mgoin's picture

Create generation_config.json

d39b09f verified 7 months ago

136 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": [128001, 128009],
	"transformers_version": "4.40.0.dev0"
	}