OPEA
/

Meta-Llama-3.1-8B-Instruct-int4-sym-inc

4-bit precision

Model card Files Files and versions

cicdatopea commited on Apr 24

Commit

42893e9

·

verified ·

1 Parent(s): cee2ad8

Update quantization_config.json

Files changed (1) hide show

quantization_config.json +1 -2

quantization_config.json CHANGED Viewed

@@ -54,6 +54,5 @@
   "enable_norm_bias_tuning": false,
   "dataset": "NeelNanda/pile-10k",
   "autoround_version": "0.4.1",
-  "quant_method": "intel/auto-round",
-  "backend": "auto_round:gptq:exllamav2"
 }

   "enable_norm_bias_tuning": false,
   "dataset": "NeelNanda/pile-10k",
   "autoround_version": "0.4.1",
+  "quant_method": "auto-round"
 }