Upload 3 files

config.json

@@ -1 +1 @@
-{"tokenizer_name": "sentence-transformers/LaBSE", "apply_pca": 256, "apply_zipf": true, "normalize": false}
+{"tokenizer_name": "sentence-transformers/LaBSE", "apply_pca": 256, "apply_zipf": true, "normalize": false, "seq_length": 1000000}

special_tokens_map.json

@@ -1 +1,7 @@
-{"cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "unk_token": "[UNK]", "mask_token": "[MASK]"}
+{
+    "cls_token": "[CLS]",
+    "sep_token": "[SEP]",
+    "pad_token": "[PAD]",
+    "unk_token": "[UNK]",
+    "mask_token": "[MASK]"
+}

tokenizer_config.json

@@ -1 +1,55 @@
-{"added_tokens_decoder": {"0": {"content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "2": {"content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "3": {"content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "4": {"content": "[MASK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}}, "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_lower_case": false, "mask_token": "[MASK]", "model_max_length": 512, "pad_token": "[PAD]", "sep_token": "[SEP]", "strip_accents": null, "tokenize_chinese_chars": true, "tokenizer_class": "BertTokenizer", "unk_token": "[UNK]"}
+{
+    "added_tokens_decoder": {
+        "0": {
+            "content": "[PAD]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "1": {
+            "content": "[UNK]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "2": {
+            "content": "[CLS]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "3": {
+            "content": "[SEP]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "4": {
+            "content": "[MASK]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "clean_up_tokenization_spaces": true,
+    "cls_token": "[CLS]",
+    "do_lower_case": false,
+    "mask_token": "[MASK]",
+    "model_max_length": 1000000,
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "strip_accents": null,
+    "tokenize_chinese_chars": true,
+    "tokenizer_class": "BertTokenizer",
+    "unk_token": "[UNK]"
+}