Upload folder using huggingface_hub

config.json

@@ -106,7 +106,7 @@
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.11.1.a20250912"
+    "version": "0.12.3.a20251114"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -114,8 +114,8 @@
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.0.dev0",
+  "transformers_version": "4.57.1",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
-}
+}

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.57.0.dev0"
+  "transformers_version": "4.57.1"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078d12c1ff7aaf6ff9a2943d06e8907de460581376ecdca38e9ca4013201c4a4
+oid sha256:ae59a04c559fd19fffb4ea029b584f4c2121fe82dfe50908ef9a5109ba1674ac
 size 5001707008

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545186f5ff36c0aa2ebc4e7b8154058d6ed3b92ec2796f9c11367e75ea357239
+oid sha256:82134082d19a2399f9e518777bd9e6d8ae5ef3bbb73a2ff4e3d4727049af7e33
 size 5001283696

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250b38969c285a6213621aef4e4cdab99a85aacda3ebaa0a18d20d788e121386
+oid sha256:3d377ef3c4f84df9711ccb5c64e2d59521839d68404544d5779340c7f2b0818d
 size 5001283912

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f157386d73df8142fafc87e23a76961d397edd37e7fa8884e588b931f8ca62c
+oid sha256:39bb63e3056ca762f9f2dbeeab33f53c74f0b8f85c584b5a2bd9ae7ac9471c54
 size 3090232736

recipe.yaml

@@ -1,5 +1,5 @@
-quant_stage:
-  quant_modifiers:
+default_stage:
+  default_modifiers:
     AWQModifier:
       config_groups:
         group_0:
@@ -13,6 +13,8 @@ quant_stage:
             block_structure: null
             dynamic: false
             actorder: null
+            scale_dtype: null
+            zp_dtype: null
             observer: mse
             observer_kwargs: {}
           input_activations: null
@@ -30,4 +32,6 @@ quant_stage:
         balance_layers: ['re:.*mlp.experts.*.gate_proj$', 're:.*mlp.experts.*.up_proj$']
       - smooth_layer: re:.*up_proj$
         balance_layers: ['re:.*down_proj$']
+      offload_device: !!python/object/apply:torch.device [cpu]
       duo_scaling: true
+      n_grid: 20

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1a036a9837df9caeebb840d09d80e8feef0f6d2bae982970d1ad34f5946aff
-size 11422753
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654