Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
TheBloke commited on
Commit
3a7a18d
1 Parent(s): 576436a

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. quantize_config.json +0 -1
quantize_config.json CHANGED
@@ -3,7 +3,6 @@
3
  "group_size": 128,
4
  "damp_percent": 0.1,
5
  "desc_act": false,
6
- "static_groups": false,
7
  "sym": true,
8
  "true_sequential": true,
9
  "model_name_or_path": null,
 
3
  "group_size": 128,
4
  "damp_percent": 0.1,
5
  "desc_act": false,
 
6
  "sym": true,
7
  "true_sequential": true,
8
  "model_name_or_path": null,