elisachen
/

bloom-GPTQquantized-multiclassification-model

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

elisachen commited on Mar 11

Commit

eb397c9

•

1 Parent(s): d2aaa7d

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -930,7 +930,7 @@
     "tokenizer": null,
     "true_sequential": true,
     "use_cuda_fp16": false,
-    "use_exllama": true
   },
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,

     "tokenizer": null,
     "true_sequential": true,
     "use_cuda_fp16": false,
+    "use_exllama": false
   },
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,