Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

special_tokens_map.json

@@ -7,14 +7,14 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": 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

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,19 +26,39 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'].strip() %}{% else %}{% set loop_messages = messages %}{% set system_message = '你是人工智慧助理，以下是用戶和人工智能助理之間的對話。你要對用戶的問題提供有用、安全、詳細和禮貌的回答。' %}{% endif %}{{system_message + eos_token}}{% for message in loop_messages %}{% if message['role'] == 'user' %}USER: {{ message['content'].strip() + eos_token }}{% elif message['role'] == 'system' %}{{message['content'].strip() + eos_token}}{% elif message['role'] == 'assistant' %}ASSISTANT: {{ message['content'].strip() + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{'ASSISTANT:'}}{% endif %}",
+  "chat_template": "{% 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": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 4096,
-  "pad_token": "<unk>",
-  "padding_side": "right",
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false,
+  "use_fast": true
 }