Upload folder using huggingface_hub

config.json

@@ -58,7 +58,7 @@
       }
     },
     "format": "int-quantized",
-    "global_compression_ratio": 1.458959021662211,
+    "global_compression_ratio": 1.5282327198317063,
     "ignore": [
       "lm_head"
     ],
@@ -77,7 +77,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.48.0",
   "use_cache": false,
   "vocab_size": 128258
 }

generation_config.json

@@ -10,5 +10,5 @@
   ],
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.48.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72689e38e01904d861bde6b93babad602483c34a197d2e1014d9ec172833f3e
+oid sha256:f513eec475d256a7f56228ad4982b406b156e04a5a5a78a6b2fa1c954d30ef1f
 size 4999417248

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baf71f14e5867c0382e0efc7cbf5618c0625c892d276deb97c0a670b65a9d2a7
+oid sha256:f7267604493236610ecb144e2b256f887388b1e5980c93a32d03019e276dad2b
 size 4084628880

recipe.yaml

@@ -3,5 +3,6 @@ DEFAULT_stage:
     SmoothQuantModifier: {smoothing_strength: 0.8}
     GPTQModifier:
       targets: Linear
+      dampening_frac: 0.1
       ignore: [lm_head]
       scheme: W8A8

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca43616769fed4807470fb41ccf7f5eebdd08624e7b9adafc09d99332cf31eb
-size 17210297
+oid sha256:fe64d8928b8843143ff63a86ef01beafd2943e72090bb5f9800db4a97f5c7e5f
+size 17210579