Upload tokenizer

special_tokens_map.json

@@ -7,14 +7,14 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": true,
     "normalized": false,
     "rstrip": true,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|dummy_85|>",
     "lstrip": true,
     "normalized": false,
     "rstrip": true,

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 4500,
+    "max_length": 2500,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -771,11 +771,11 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 4500,
-  "pad_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2500,
+  "pad_token": "<|dummy_85|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }