Intel
/

phi-2-int4-inc

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

intel/auto-round

Model card Files Files and versions Community

phi-2-int4-inc / model.safetensors

Commit History

upload auto_gptq format

5973e3a

n1ck-guo commited on about 1 month ago

replace with sym quantization as there is a large accuracy drop due to kernel issue

f201b74

wenhuach commited on May 27

first commit

3516d2e

wenhuach commited on Feb 22