Upload folder using huggingface_hub

config.json

@@ -31,9 +31,11 @@
           "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
+          "scale_dtype": null,
           "strategy": "tensor",
           "symmetric": true,
-          "type": "int"
+          "type": "int",
+          "zp_dtype": null
         },
         "output_activations": null,
         "targets": [
@@ -47,9 +49,11 @@
           "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
+          "scale_dtype": null,
           "strategy": "channel",
           "symmetric": true,
-          "type": "int"
+          "type": "int",
+          "zp_dtype": null
         }
       }
     },
@@ -63,13 +67,13 @@
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.12.3.a20251030"
+    "version": "0.12.3.a20251114"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.1",
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.57.1"
+  "transformers_version": "4.57.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6b05b011ae763f08e8abab3bdf5c9a43bfe113d3d4e6860fab62268c8ae8dd
+oid sha256:9fa2f9db57cf24502a1d2b0cb1dc3788199a7a3730864425bbdc497ee849e534
 size 1232059012

recipe.yaml

@@ -23,6 +23,8 @@ quant_stage:
             block_structure: null
             dynamic: false
             actorder: null
+            scale_dtype: null
+            zp_dtype: null
             observer: minmax
             observer_kwargs: {}
           input_activations:
@@ -34,6 +36,8 @@ quant_stage:
             block_structure: null
             dynamic: false
             actorder: null
+            scale_dtype: null
+            zp_dtype: null
             observer: minmax
             observer_kwargs: {}
           output_activations: null

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723