對tokenizer增加special tokens使其能被.apply_chat_template正確轉換 (#36)

- 對tokenizer增加special tokens使其能被.apply_chat_template正確轉換 (fa96a49c9c51c84f9b85a7ddde27d9241ca82901)


Co-authored-by: Philip Huang <[email protected]>

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer_config.json

@@ -1,13 +1,52 @@
 {
-  "name_or_path": "THUDM/chatglm3-6b",
-  "remove_space": false,
-  "do_lower_case": false,
-  "tokenizer_class": "ChatGLMTokenizer",
-  "chat_template": "{% for message in messages %}{% if loop.first %}[gMASK]sop<|{{ message['role'] }}|> \n {{ message['content'] }}{% else %}<|{{ message['role'] }}|> \n {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
+  "added_tokens_decoder": {
+    "64790": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64792": {
+      "content": "sop",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64795": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64796": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
   "auto_map": {
     "AutoTokenizer": [
-      "tokenization_chatglm.ChatGLMTokenizer",
+      "THUDM/chatglm3-6b--tokenization_chatglm.ChatGLMTokenizer",
       null
-      ]
-  }
+    ]
+  },
+  "chat_template": "{% for message in messages %}{% if loop.first %}[gMASK]sop<|{{ message['role'] }}|>\n {{ message['content'] }}{% else %}<|{{ message['role'] }}|>\n {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "unk_token": "<unk>"
 }