nm-testing
/

w4a16_grouped_quant-e2e

compressed-tensors

Model card Files Files and versions

nm-autobot commited on about 13 hours ago

Commit

61b7918

·

verified ·

1 Parent(s): 229b757

Upload folder using huggingface_hub

Files changed (2) hide show

config.json +2 -2
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -28,7 +28,7 @@
           "dynamic": false,
           "group_size": 128,
           "num_bits": 4,
-          "observer": "memoryless_minmax",
           "strategy": "group",
           "symmetric": true,
           "type": "int"
@@ -46,7 +46,7 @@
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.20.2a20261103"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

           "dynamic": false,
           "group_size": 128,
           "num_bits": 4,
+          "observer": "imatrix_mse",
           "strategy": "group",
           "symmetric": true,
           "type": "int"
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
+    "version": "0.20.2.dev7+g222b8957"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038483e85faabe272200101c502d91e5dd9e566d677879eae63eff65aab5b4b9
 size 761968800

 version https://git-lfs.github.com/spec/v1
+oid sha256:f5c047c1270579b5035bb5a421fcb35978cb30545dfdd0064682893ee9ea1099
 size 761968800