Upload tokenizer

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
-  "bos_token": "<s>",
+  "bos_token": "</s>",
   "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "pad_token": "<unk>",
+  "unk_token": "</s>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:70fdeca54820d72c23bf82e76b491200fb0a84bcd0f3391c7a20334b041e8a70
+size 1842667

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,11 +1,33 @@
 {
-  "add_prefix_space": false,
-  "bos_token": "<s>",
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "padding_side": "left",
-  "tokenizer_class": "BloomTokenizer",
-  "unk_token": "<unk>"
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }