Updated the tokenizer to latest from mistralai/Mistral-Nemo-Base-2407 to make the model llama.cpp compatible

tokenizer.json

@@ -9002,24 +9002,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 131072,
-      "content": "<|im_end|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 131073,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
     }
   ],
   "normalizer": null,
@@ -9056,12 +9038,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -9077,12 +9053,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -9094,12 +9064,6 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
@@ -8000,30 +8002,12 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "131072": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "131073": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<|im_end|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "tokenizer_class": "GPT2Tokenizer",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }