Fix configs

generation_config.json

@@ -1,6 +1,8 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.43.4"
+  "eos_token_id": 32001,
+  "pad_token": 2,
+  "unk_token": 0,
+  "transformers_version": "4.39.3"
 }

special_tokens_map.json

@@ -137,7 +137,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1203,6 +1203,12 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
       {
         "Sequence": {
           "id": "A",
@@ -1211,12 +1217,24 @@
       }
     ],
     "pair": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 1
+        }
+      },
       {
         "Sequence": {
           "id": "B",
@@ -1224,7 +1242,17 @@
         }
       }
     ],
-    "special_tokens": {}
+    "special_tokens": {
+      "<s>": {
+        "id": "<s>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<s>"
+        ]
+      }
+    }
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json

@@ -1185,7 +1185,7 @@
   "bos_token": "<s>",
   "chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",