Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft__Phi-3-medium-128k-instruct",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--microsoft--Phi-3-medium-128k-instruct/snapshots/cae1d42b5577398fd1be9f0746052562ae552886",
   "architectures": [
     "Phi3ForCausalLM"
   ],
@@ -38,13 +38,7 @@
     ],
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
-    "quantization_status": "frozen",
-    "sparsity_config": {
-      "format": "dense",
-      "global_sparsity": 1.3619957547314265,
-      "registry_requires_subclass": false,
-      "sparsity_structure": "unstructured"
-    }
+    "quantization_status": "frozen"
   },
   "embd_pdrop": 0.0,
   "eos_token_id": 32000,
@@ -200,7 +194,7 @@
   "sliding_window": 131072,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 32064
 }

generation_config.json

@@ -7,5 +7,5 @@
     32007
   ],
   "pad_token_id": 32000,
-  "transformers_version": "4.42.3"
+  "transformers_version": "4.44.0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c78c728fbf14bc3c71982b7d19f55c7654adf1ed662a166bb98bf624fdf82df
+oid sha256:b996802f676dfe1a9b7ec85969c81460b59b1d7a8f4c26dd9a40e0cc8e2dd370
 size 4825817208

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f671b14a63c738d3865603c44c9d4792fc1cf10979a26ad94ba36d13c001fe
+oid sha256:8d0b30886ec45d29d9ec24d32bcb232657c55e06f90e5695a17fa212475f6037
 size 4956409160

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b763d02e15c5bd3c05398a3adab890e84c84208778d480f5b94fc00092f93da7
+oid sha256:1843b208a870fb88b9d4d98abe7b683226b9671eb88b503c9db7fbf707d160fc
 size 4511129936

recipe.yaml

@@ -4,7 +4,5 @@ quant_stage:
       sequential_update: false
       dampening_frac: 0.01
       ignore: [lm_head]
-      config_groups:
-        group_0:
-          targets: [Linear]
-          weights: {num_bits: 8, type: int, symmetric: true, strategy: channel}
+      scheme: W8A16
+      targets: Linear