Upload tokenizer

merges.txt

@@ -49741,4 +49741,3 @@ Cihaz ın
 Ġistek te
 Ġkendimiz in
 Su eno
-Ġolm u

special_tokens_map.json

@@ -7,6 +7,13 @@
     "single_word": false
   },
   "eos_token": {
+    "content": "<|stop|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,

tokenizer_config.json

@@ -9,14 +9,23 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "1": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
+  "chat_template": "{% set message_count = messages|length %}{% if message_count >= 4 and messages[-4].role == 'user' %}{% set recent_messages = messages[-4:] %}{% elif message_count > 3 %}{% set recent_messages = messages[-3:] %}{% else %}{% set recent_messages = messages %}{% endif %}{% for message in recent_messages %}{% if message.role == 'user' %}### Kullanıcı:\n{{ message.content }}\n{% elif message.role == 'assistant' %}### Asistan:\n{{ message.content }}\n{% endif %}{% endfor %}{% if messages[-1]['role'] == 'user' %}### Asistan:\n{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|stop|>",
   "errors": "replace",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }