q10
/

Qwen3-8B-Base-INT8-INT4

Text Generation

text-generation-inference

Model card Files Files and versions

q10 commited on Aug 25

Commit

9da3ea0

·

verified ·

1 Parent(s): 3149ba3

Upload Qwen3ForCausalLM

Files changed (1) hide show

config.json +4 -0

config.json CHANGED Viewed

@@ -115,6 +115,10 @@
                   "_data": "SYMMETRIC",
                   "_type": "MappingType"
                 },
                 "scale_dtype": null,
                 "weight_dtype": {
                   "_data": "int8",

                   "_data": "SYMMETRIC",
                   "_type": "MappingType"
                 },
+                "packing_format": {
+                  "_data": "UNPACKED_TO_INT8",
+                  "_type": "PackingFormat"
+                },
                 "scale_dtype": null,
                 "weight_dtype": {
                   "_data": "int8",