tokenizer_mod

special_tokens_map.json

@@ -1,28 +1,34 @@
 {
   "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
+    "<unk>",
+    "<s>",
+    "</s>"
   ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -3,7 +3,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -11,7 +11,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -19,38 +19,6 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32000": {
-      "content": "▁<PRE>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "▁<MID>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "▁<SUF>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "▁<EOT>",
-      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
@@ -58,24 +26,21 @@
     }
   },
   "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
+    "<unk>",
+    "<s>",
+    "</s>"
   ],
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "eot_token": "▁<EOT>",
-  "fill_token": "<FILL_ME>",
-  "legacy": null,
-  "middle_token": "▁<MID>",
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "prefix_token": "▁<PRE>",
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
-  "suffix_token": "▁<SUF>",
-  "tokenizer_class": "CodeLlamaTokenizer",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": true
 }