neuralmagic
/

Phi-3-mini-128k-instruct-FP8

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

Lin-K76 commited on Aug 12

Commit

ba410c9

•

1 Parent(s): f5543ba

Upload folder using huggingface_hub

Files changed (2) hide show

config.json +2 -2
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -41,7 +41,7 @@
         }
       }
     },
-    "format": "naive-quantized",
     "global_compression_ratio": 1.246153835878366,
     "ignore": [
       "lm_head"
@@ -172,7 +172,7 @@
   "sliding_window": 262144,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.44.0.dev0",
   "use_cache": true,
   "vocab_size": 32064
 }

         }
       }
     },
+    "format": "float-quantized",
     "global_compression_ratio": 1.246153835878366,
     "ignore": [
       "lm_head"
   "sliding_window": 262144,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 32064
 }

generation_config.json CHANGED Viewed

@@ -7,5 +7,5 @@
     32007
   ],
   "pad_token_id": 32000,
-  "transformers_version": "4.44.0.dev0"
 }

     32007
   ],
   "pad_token_id": 32000,
+  "transformers_version": "4.44.0"
 }