fix(tokenizer): fix it

generation_config.json

@@ -1,9 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 100257,
-  "eos_token_id": [
-    100257,
-    100265
-  ],
-  "transformers_version": "4.47.0"
-}
+  "eos_token_id": 100265,
+  "pad_token_id": 100351,
+  "transformers_version": "4.47.1"
+}

special_tokens_map.json

@@ -7,18 +7,18 @@
     "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_87|>",
     "lstrip": true,
     "normalized": false,
     "rstrip": true,
     "single_word": false
   },
-  "unk_token": "<|endoftext|>"
-}
+  "unk_token": "�"
+}

tokenizer.json

@@ -3,6 +3,15 @@
   "truncation": null,
   "padding": null,
   "added_tokens": [
+    {
+      "id": 5809,
+      "content": "�",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
     {
       "id": 100256,
       "content": "<|dummy_0|>",

tokenizer_config.json

@@ -1,6 +1,14 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
+    "5809": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "100256": {
       "content": "<|dummy_0|>",
       "lstrip": true,
@@ -771,12 +779,13 @@
     }
   },
   "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|>",
+  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 16384,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|dummy_87|>",
+  "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}
+  "unk_token": "�"
+}