Upload tokenizer

added_tokens.json

@@ -1,3 +1,5 @@
 {
-  "<|pad|>": 52928
+  "<|bos|>": 51904,
+  "<|eos|>": 51905,
+  "<|pad|>": 51906
 }

special_tokens_map.json

@@ -1,19 +1,25 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|bos|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|eos|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|pad|>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3607f62751f5595f4f135617e930cf34a11213803db34898a7c9c942ec18c0
-size 827711
+oid sha256:707b7199a4a7bcf18c01be43e2ba1709a4366dca255d54dc36ec432816766b30
+size 780938

tokenizer_config.json

@@ -3,7 +3,7 @@
   "add_eos_token": true,
   "bos_token": {
     "__type": "AddedToken",
-    "content": "<s>",
+    "content": "<|bos|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
@@ -12,14 +12,21 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": {
     "__type": "AddedToken",
-    "content": "</s>",
+    "content": "<|eos|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {