styalai
/

phi-2_quantize_gptq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

phi-2_quantize_gptq / generation_config.json

styalai's picture

Upload PhiForCausalLM

d6ef5c8 verified 8 months ago

119 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 50256,
	"eos_token_id": 50256,
	"transformers_version": "4.38.2"
	}