bobbydeveloper2014
/

deepseek-coder-6.7b-quanto-int4

8-bit precision

Model card Files Files and versions

deepseek-coder-6.7b-quanto-int4

Commit History

Upload Quanto int4 quantized model (with safe_save)

c3037e3
verified

bobbydeveloper2014 commited on Jul 5

Upload Quanto int4 quantized model (with manual quanto_qmap.json)

f00ab23
verified

bobbydeveloper2014 commited on Jul 4

Delete pytorch_model.bin

2ab4179
verified

bobbydeveloper2014 commited on Jul 4

Upload Quanto int4 quantized model (fixed)

081f944
verified

bobbydeveloper2014 commited on Jul 4

Upload Quanto int4 quantized model

dd2293d
verified

bobbydeveloper2014 commited on Jul 4

initial commit

e979e6c
verified

bobbydeveloper2014 commited on Jul 4