nm-testing
/

asym-w8w8-int8-static-per-tensor-tiny-llama

8-bit precision

compressed-tensors

Model card Files Files and versions

asym-w8w8-int8-static-per-tensor-tiny-llama

1.23 GB

2 contributors

History: 3 commits

mgoin's picture

Updated compression_config to quantization_config

8cd9cab verified over 1 year ago