Upload tokenizer

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -36,13 +31,23 @@
       "special": true
     }
   ],
-  "normalizer": null,
-  "pre_tokenizer": {
-    "type": "Metaspace",
-    "replacement": "▁",
-    "prepend_scheme": "first",
-    "split": false
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Prepend",
+        "prepend": "▁"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": " "
+        },
+        "content": "▁"
+      }
+    ]
   },
+  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
@@ -129,7 +134,6 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
-    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -1,43 +1,35 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "legacy": false,
   "model_max_length": 4096,
-  "pad_token": "</s>",
+  "pad_token": null,
   "padding_side": "right",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }