Upload 5 files

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Phillnet.png filter=lfs diff=lfs merge=lfs -text
 Model_Overview.png filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text

optimizer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baeabefd42201c6174aa5e7478f82e9aaec22e292c465e8dd44a7a8238f9ada8
+size 2838829242

special_tokens_map.json

@@ -108,13 +108,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -1064,6 +1076,15 @@
       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 32114,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,4 +1,10 @@
 {
+  "adaptive_tokenization": {
+    "enable": true,
+    "max_tokens": 100000,
+    "min_frequency": 3,
+    "retain_variant_forms": true
+  },
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",
@@ -943,6 +949,14 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "32114": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -1047,24 +1061,40 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
+  "bpe_dropout": 0.1,
   "clean_up_tokenization_spaces": true,
+  "enable_token_classification": true,
   "eos_token": "</s>",
   "extra_ids": 100,
   "max_length": 1024,
   "model_max_length": 1024,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "tokenizer_class": "T5Tokenizer",
-  "unk_token": "<unk>",
-  "enable_token_classification": true,
   "normalization_rules": {
     "enable": true,
     "lowercase": true,
-    "strip_accents": true,
+    "nmt_normalization": true,
     "pre_tokenization": {
       "punctuation_split": true,
       "split_digits": true
-    }
-  }
-}
+    },
+    "strip_accents": true
+  },
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "spe_tokenization": {
+    "coverage": 0.9995,
+    "enable": true,
+    "nbest_size": 64
+  },
+  "stride": 0,
+  "subword_regularization": {
+    "alpha": 0.1,
+    "dropout": 0.1,
+    "enable": true
+  },
+  "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}