baseten-admin
/

glm-4.6-fp4-mlp

8-bit precision

Model card Files Files and versions

baseten-admin commited on Oct 6

Commit

1435ad8

·

verified ·

1 Parent(s): 23f9b56

Update config.json

Files changed (1) hide show

config.json +2 -1

config.json CHANGED Viewed

@@ -153,7 +153,8 @@
             "model.layers.9.self_attn*",
             "model.layers.90.self_attn*",
             "model.layers.91.self_attn*",
-            "lm_head"
         ],
         "quant_algo": "NVFP4",
         "producer": {

             "model.layers.9.self_attn*",
             "model.layers.90.self_attn*",
             "model.layers.91.self_attn*",
+            "lm_head",
+            "model.layers.92*"
         ],
         "quant_algo": "NVFP4",
         "producer": {