Upload folder using huggingface_hub

config.json

@@ -29,36 +29,28 @@
       "group_0": {
         "format": "nvfp4-pack-quantized",
         "input_activations": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": "local",
           "group_size": 16,
           "num_bits": 4,
           "observer": "static_minmax",
-          "observer_kwargs": {},
           "scale_dtype": "torch.float8_e4m3fn",
           "strategy": "tensor_group",
           "symmetric": true,
-          "type": "float",
-          "zp_dtype": null
+          "type": "float"
         },
         "output_activations": null,
         "targets": [
           "Linear"
         ],
         "weights": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": false,
           "group_size": 16,
           "num_bits": 4,
           "observer": "memoryless_minmax",
-          "observer_kwargs": {},
           "scale_dtype": "torch.float8_e4m3fn",
           "strategy": "tensor_group",
           "symmetric": true,
-          "type": "float",
-          "zp_dtype": null
+          "type": "float"
         }
       }
     },
@@ -116,11 +108,12 @@
       "lm_head"
     ],
     "kv_cache_scheme": null,
+    "moe_sparsity_config": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.19.1.dev0"
+    "version": "0.19.1.dev41+g0ccb6a99"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "5.17.0"
+  "transformers_version": "5.20.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a5bfd37cf24d2749f37bb6cb2021fcecc187d9832ef037e4e33a133fef614b
+oid sha256:c22fdcdff49b38f6bafdb8cdf5f5f2bb5bbd76ef1df61bd9f276d13ff855fd8e
 size 18096813840