LoftQ
/

Phi-3-mini-4k-instruct-4bit-64rank

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Phi-3-mini-4k-instruct-4bit-64rank / generation_config.json

LoftQ's picture

Upload folder using huggingface_hub

7d627f9 verified 6 months ago

172 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": [
	32000,
	32001,
	32007
	],
	"pad_token_id": 32000,
	"transformers_version": "4.40.1"
	}