feat add pad_token

special_tokens_map.json

@@ -32,7 +32,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -18212,7 +18212,7 @@
     },
     {
       "id": 2023,
-      "content": ">>UNUSED_1897<<",
+      "content": "<|pad|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -20280,7 +20280,7 @@
       ">>UNUSED_1894<<": 2020,
       ">>UNUSED_1895<<": 2021,
       ">>UNUSED_1896<<": 2022,
-      ">>UNUSED_1897<<": 2023,
+      "<|pad|>": 2023,
       "!": 2024,
       "\"": 2025,
       "#": 2026,

tokenizer_config.json

@@ -16186,7 +16186,7 @@
       "special": true
     },
     "2023": {
-      "content": ">>UNUSED_1897<<",
+      "content": "<|pad|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -16219,7 +16219,6 @@
     ">>PASSWORD<<",
     ">>KEY<<"
   ],
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n'  + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
@@ -16227,7 +16226,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 8192,
-  "pad_token": "<|endoftext|>",
+  "model_max_length": 32768,
+  "pad_token": "<|pad|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }