Upload tokenizer

special_tokens_map.json

@@ -1,29 +1,22 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
+    "content": "<|pad|>",
     "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -5,29 +5,56 @@
   "added_tokens": [
     {
       "id": 0,
-      "content": "<unk>",
+      "content": "<|pad|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
       "id": 1,
-      "content": "<s>",
+      "content": "<|begin_of_text|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
       "id": 2,
-      "content": "</s>",
+      "content": "<|end_of_text|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "<|eot_id|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
+      "content": "<|start_header_id|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 7,
+      "content": "<|end_header_id|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
       "special": true
     }
   ],
@@ -101,20 +128,21 @@
   "model": {
     "type": "BPE",
     "dropout": null,
-    "unk_token": "<unk>",
+    "unk_token": null,
     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
-      "<unk>": 0,
-      "<s>": 1,
-      "</s>": 2,
+      "<|pad|>": 0,
+      "<|begin_of_text|>": 1,
+      "<|end_of_text|>": 2,
       "\t": 3,
       "▁▁": 4,
-      "<reserved_2>": 5,
-      "<reserved_3>": 6,
-      "<reserved_4>": 7,
+      "<|eot_id|>": 5,
+      "<|start_header_id|>": 6,
+      "<|end_header_id|>": 7,
       "\n": 8,
       "<h2>": 9,
       "<h2/>": 10,

tokenizer_config.json

@@ -1,44 +1,67 @@
 {
   "add_bos_token": false,
   "add_eos_token": false,
-  "add_prefix_space": true,  
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "<|pad|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "<|begin_of_text|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "<|end_of_text|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if loop.first %}{{ bos_token }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] + '\n\nAssistant: ' + eos_token }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}",
+  "bos_token": "<|begin_of_text|>",
+  "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": false,
-  "eos_token": "</s>",
+  "eos_token": "<|end_of_text|>",
   "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<unk>",
+  "model_max_length": 200000,
+  "pad_token": "<|pad|>",
   "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "use_default_system_prompt": false
 }