Upload folder using huggingface_hub

.gitattributes

@@ -0,0 +1,2 @@
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -129,25 +129,41 @@
             },
             "model.embed_tokens": {
               "_data": {
-                "activation_quantization": "int8_asym_per_token",
-                "b": 2,
-                "granularity": {
+                "act_mapping_type": {
+                  "_data": "ASYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "intx_choose_qparams_algorithm": {
+                  "_data": "AFFINE",
+                  "_type": "IntxChooseQParamsAlgorithm"
+                },
+                "intx_packing_format": {
+                  "_data": "UNPACKED_TO_INT8",
+                  "_type": "IntxPackingFormat"
+                },
+                "layout": {
+                  "_data": {},
+                  "_type": "QDQLayout",
+                  "_version": 1
+                },
+                "weight_dtype": {
+                  "_data": "int4",
+                  "_type": "torch.dtype"
+                },
+                "weight_granularity": {
                   "_data": {
                     "axis": 0
                   },
                   "_type": "PerAxis",
                   "_version": 1
                 },
-                "layout": {
-                  "_data": {},
-                  "_type": "QDQLayout",
-                  "_version": 1
+                "weight_mapping_type": {
+                  "_data": "SYMMETRIC",
+                  "_type": "MappingType"
                 },
-                "quant_max": 1.5,
-                "quant_min": -1.5,
-                "scale_dtype": null
+                "weight_scale_dtype": null
               },
-              "_type": "StretchedIntxWeightConfig",
+              "_type": "Int8DynamicActivationIntxWeightConfig",
               "_version": 2
             }
           }