Upload folder using huggingface_hub

config.json

@@ -21,19 +21,24 @@
     "global_compression_ratio": null,
     "ignore": [],
     "kv_cache_scheme": {
+      "actorder": null,
+      "block_structure": null,
       "dynamic": false,
       "group_size": null,
       "num_bits": 8,
+      "observer": null,
+      "observer_kwargs": {},
+      "scale_dtype": null,
       "strategy": "tensor",
       "symmetric": true,
-      "type": "float"
+      "type": "float",
+      "zp_dtype": null
     },
-    "moe_sparsity_config": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.19.1.dev41+g0ccb6a99"
+    "version": "0.19.0"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "5.20.2"
+  "transformers_version": "5.17.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d7409b608302eaa005d80fa8e7399a0100c989ea930255672afa115cbba972
+oid sha256:72ac17f5b6042ba4bdd33bc44fb95157f06aea09555bc60599eacc0b890bb907
 size 2200124472

recipe.yaml

@@ -3,7 +3,18 @@ quant_stage:
     QuantizationModifier:
       targets: [Linear]
       ignore: []
-      kv_cache_scheme: {num_bits: 8, type: float, symmetric: true, group_size: null, strategy: tensor,
-        dynamic: false}
+      kv_cache_scheme:
+        num_bits: 8
+        type: float
+        symmetric: true
+        group_size: null
+        strategy: tensor
+        block_structure: null
+        dynamic: false
+        actorder: null
+        scale_dtype: null
+        zp_dtype: null
+        observer: null
+        observer_kwargs: {}
       bypass_divisibility_checks: false
       requires_calibration_data: true