Upload tokenizer

added_tokens.json

@@ -1,8 +1,5 @@
 {
   "\n\n### Instruction:\n": 65107,
   "\n\n### Response:\n": 65108,
-  "</s>": 2,
-  "<pad>": 65109,
-  "<s>": 1,
-  "<unk>": 0
+  "<pad>": 65109
 }

special_tokens_map.json

@@ -1,14 +1,34 @@
 {
   "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>",
     "\n\n### Instruction:\n",
-    "\n\n### Response:\n",
-    "<pad>"
+    "\n\n### Response:\n"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -34,8 +34,8 @@
       "id": 65107,
       "content": "\n\n### Instruction:\n",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -43,8 +43,8 @@
       "id": 65108,
       "content": "\n\n### Response:\n",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -54,7 +54,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     }
   ],

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": false,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -28,47 +26,42 @@
     },
     "65107": {
       "content": "\n\n### Instruction:\n",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "65108": {
       "content": "\n\n### Response:\n",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "65109": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>",
     "\n\n### Instruction:\n",
-    "\n\n### Response:\n",
-    "<pad>"
+    "\n\n### Response:\n"
   ],
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n### Instruction:\n' }}{% elif message['role'] == 'assistant' %}{{ '\n\n### Response:\n' }}{% endif %}{{ message['content'] }}{{ eos_token }}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true,
-  "use_fast": true
+  "use_default_system_prompt": false
 }