Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|eom_id|>": 32769,
+  "<|eot_id|>": 32768
+}

special_tokens_map.json

@@ -1,4 +1,13 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -7,13 +16,19 @@
     "single_word": false
   },
   "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
     "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c3fc985cbfedcb429d05994efe548bdfecd6a00226fcdc8380c36fd894a3be
-size 3671968
+oid sha256:207b7554d70eb387ac7cbd081d396c5caa7fa8b5db7a665a17f9ebc7e12a4a68
+size 3672340

tokenizer_config.json

@@ -6170,11 +6170,30 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32768": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32769": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|eom_id|>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,