Upload tokenizer

special_tokens_map.json

@@ -1,5 +1,23 @@
 {
-  "bos_token": "<|begin_of_text|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|finetune_right_pad_id|>"
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f4a1a7159f2dacfa01410288c1b9faee8d5e309c880cb3dfc8e9ab3e070cef
-size 17209915
+oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
+size 17209530

tokenizer_config.json

@@ -1,7 +1,10 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "128000": {
-      "content": "<|begin_of_text|>",
+      "content": "<｜begin▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +12,7 @@
       "special": true
     },
     "128001": {
-      "content": "<|im_end|>",
+      "content": "<｜end▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -89,39 +92,39 @@
       "special": true
     },
     "128011": {
-      "content": "<|reserved_special_token_3|>",
+      "content": "<｜User｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128012": {
-      "content": "<|reserved_special_token_4|>",
+      "content": "<｜Assistant｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128013": {
-      "content": "<|reserved_special_token_5|>",
+      "content": "<think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128014": {
-      "content": "<|reserved_special_token_6|>",
+      "content": "</think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128015": {
-      "content": "<|reserved_special_token_7|>",
+      "content": "<｜▁pad▁｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2049,13 +2052,17 @@
       "special": true
     }
   },
-  "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<｜end▁of▁sentence｜>",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": true,
+  "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": null
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
 }