kaitchup
/

Llama-2-7b-gptq-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

bnjmnmarie commited on Dec 19, 2023

Commit

dd2921e

•

1 Parent(s): 5332cea

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
     "damp_percent": 0.1,
     "dataset": "c4",
     "desc_act": false,
-    "disable_exllama": false,
     "group_size": 128,
     "model_seqlen": 4096,
     "module_name_preceding_first_block": [

     "damp_percent": 0.1,
     "dataset": "c4",
     "desc_act": false,
+    "disable_exllama": true,
     "group_size": 128,
     "model_seqlen": 4096,
     "module_name_preceding_first_block": [