OPEA
/

Qwen2.5-14B-Instruct-int4-sym-inc

4-bit precision

Model card Files Files and versions

cicdatopea commited on Apr 30

Commit

0e21a49

·

verified ·

1 Parent(s): 770bd32

Update config.json

Files changed (1) hide show

config.json +0 -1

config.json CHANGED Viewed

@@ -33,7 +33,6 @@
     "lr": 0.001,
     "minmax_lr": 0.001,
     "nsamples": 512,
-    "quant_block_list": null,
     "quant_method": "auto-round",
     "scale_dtype": "torch.float16",
     "seqlen": 2048,

     "lr": 0.001,
     "minmax_lr": 0.001,
     "nsamples": 512,
     "quant_method": "auto-round",
     "scale_dtype": "torch.float16",
     "seqlen": 2048,