Intel
/

phi-2-int4-inc

Text Generation

text-generation-inference

4-bit precision

intel/auto-round

Model card Files Files and versions

phi-2-int4-inc / tokenizer.json

wenhuach's picture

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

f201b74 over 1 year ago

2.11 MB

File too large to display, you can check the raw version instead.