nm-testing
/

convert_modelopt_nvfp4-e2e

Text Generation

Model Optimizer

8-bit precision

compressed-tensors

Model card Files Files and versions

nm-autobot commited on Sep 3

Commit

376bb3e

·

verified ·

1 Parent(s): 9541cf8

Upload folder using huggingface_hub

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -84,7 +84,7 @@
           "dynamic": false,
           "group_size": 16,
           "num_bits": 4,
-          "observer": "memoryless_minmax",
           "observer_kwargs": {},
           "scale_dtype": "torch.float8_e4m3fn",
           "strategy": "tensor_group",
@@ -103,7 +103,7 @@
       "dynamic": false,
       "group_size": null,
       "num_bits": 8,
-      "observer": "memoryless_minmax",
       "observer_kwargs": {},
       "scale_dtype": null,
       "strategy": "tensor",
@@ -113,7 +113,7 @@
     },
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
-    "version": "0.18.1.a20260827"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

           "dynamic": false,
           "group_size": 16,
           "num_bits": 4,
+          "observer": null,
           "observer_kwargs": {},
           "scale_dtype": "torch.float8_e4m3fn",
           "strategy": "tensor_group",
       "dynamic": false,
       "group_size": null,
       "num_bits": 8,
+      "observer": null,
       "observer_kwargs": {},
       "scale_dtype": null,
       "strategy": "tensor",
     },
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
+    "version": "0.18.1.a20260902"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,