boboliu
/

bge-reranker-v2-minicpm-layerwise-gptq

Text Generation

4-bit precision

Model card Files Files and versions Community

boboliu commited on Sep 14

Commit

94eec71

•

1 Parent(s): d2fccc6

disable exllama

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -47,7 +47,7 @@
     "tokenizer": null,
     "true_sequential": true,
     "use_cuda_fp16": false,
-    "use_exllama": true
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

     "tokenizer": null,
     "true_sequential": true,
     "use_cuda_fp16": false,
+    "use_exllama": false
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,