woodchen7 commited on
Commit
e07c290
·
verified ·
1 Parent(s): f2cdfa8

Upload hf_quant_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. hf_quant_config.json +12 -0
hf_quant_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quantization": {
3
+ "exclude_modules": [
4
+ "lm_head",
5
+ "model.embed_tokens",
6
+ "lm_head"
7
+ ],
8
+ "kv_cache_quant_algo": null,
9
+ "quant_algo": "NVFP4",
10
+ "group_size": 16
11
+ }
12
+ }