Upload tokenizer

special_tokens_map.json

@@ -7,13 +7,6 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
     "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,

tokenizer.json

@@ -2334,10 +2334,69 @@
     ]
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": true,
-    "trim_offsets": false,
-    "use_regex": true
+    "type": "Sequence",
+    "processors": [
+      {
+        "type": "ByteLevel",
+        "add_prefix_space": true,
+        "trim_offsets": false,
+        "use_regex": true
+      },
+      {
+        "type": "TemplateProcessing",
+        "single": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          }
+        ],
+        "pair": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          },
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 1
+            }
+          },
+          {
+            "Sequence": {
+              "id": "B",
+              "type_id": 1
+            }
+          }
+        ],
+        "special_tokens": {
+          "<|begin_of_text|>": {
+            "id": "<|begin_of_text|>",
+            "ids": [
+              128000
+            ],
+            "tokens": [
+              "<|begin_of_text|>"
+            ]
+          }
+        }
+      }
+    ]
   },
   "decoder": {
     "type": "ByteLevel",
@@ -2353,7 +2412,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
-    "ignore_merges": false,
+    "ignore_merges": true,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -2050,18 +2050,15 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\\n\\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
+  "eos_token": "<|end_of_text|>",
   "max_length": 2048,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|end_of_text|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
   "stride": 0,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "truncation_side": "right",