Upload Llama-3.1-8B quantized with ModelOpt NVFP4

config.json

@@ -33,7 +33,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.3",
+  "transformers_version": "4.57.5",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   ],
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.57.3"
+  "transformers_version": "4.57.5"
 }