Update tokenizer

special_tokens_map.json

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403

tokenizer_config.json

@@ -17,20 +17,20 @@
       "special": true
     },
     "128002": {
-      "content": "<|reserved_special_token_0|>",
+      "content": "<tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128003": {
-      "content": "<|reserved_special_token_1|>",
+      "content": "<tool_response>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128004": {
       "content": "<|finetune_right_pad_id|>",
@@ -89,239 +89,239 @@
       "special": true
     },
     "128011": {
-      "content": "<|reserved_special_token_3|>",
+      "content": "<tools>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128012": {
-      "content": "<|reserved_special_token_4|>",
+      "content": "</tools>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128013": {
-      "content": "<|reserved_special_token_5|>",
+      "content": "</tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128014": {
-      "content": "<|reserved_special_token_6|>",
+      "content": "</tool_response>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128015": {
-      "content": "<|reserved_special_token_7|>",
+      "content": "<schema>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128016": {
-      "content": "<|reserved_special_token_8|>",
+      "content": "</schema>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128017": {
-      "content": "<|reserved_special_token_9|>",
+      "content": "<scratch_pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128018": {
-      "content": "<|reserved_special_token_10|>",
+      "content": "</scratch_pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128019": {
-      "content": "<|reserved_special_token_11|>",
+      "content": "<SCRATCHPAD>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128020": {
-      "content": "<|reserved_special_token_12|>",
+      "content": "</SCRATCHPAD>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128021": {
-      "content": "<|reserved_special_token_13|>",
+      "content": "<REASONING>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128022": {
-      "content": "<|reserved_special_token_14|>",
+      "content": "</REASONING>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128023": {
-      "content": "<|reserved_special_token_15|>",
+      "content": "<INNER_MONOLOGUE>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128024": {
-      "content": "<|reserved_special_token_16|>",
+      "content": "</INNER_MONOLOGUE>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128025": {
-      "content": "<|reserved_special_token_17|>",
+      "content": "<PLAN>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128026": {
-      "content": "<|reserved_special_token_18|>",
+      "content": "</PLAN>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128027": {
-      "content": "<|reserved_special_token_19|>",
+      "content": "<EXECUTION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128028": {
-      "content": "<|reserved_special_token_20|>",
+      "content": "</EXECUTION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128029": {
-      "content": "<|reserved_special_token_21|>",
+      "content": "<REFLECTION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128030": {
-      "content": "<|reserved_special_token_22|>",
+      "content": "</REFLECTION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128031": {
-      "content": "<|reserved_special_token_23|>",
+      "content": "<THINKING>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128032": {
-      "content": "<|reserved_special_token_24|>",
+      "content": "</THINKING>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128033": {
-      "content": "<|reserved_special_token_25|>",
+      "content": "<SOLUTION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128034": {
-      "content": "<|reserved_special_token_26|>",
+      "content": "</SOLUTION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128035": {
-      "content": "<|reserved_special_token_27|>",
+      "content": "<EXPLANATION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128036": {
-      "content": "<|reserved_special_token_28|>",
+      "content": "</EXPLANATION>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128037": {
-      "content": "<|reserved_special_token_29|>",
+      "content": "<UNIT_TEST>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128038": {
-      "content": "<|reserved_special_token_30|>",
+      "content": "</UNIT_TEST>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128039": {
-      "content": "<|reserved_special_token_31|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128040": {
-      "content": "<|reserved_special_token_32|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2050,13 +2050,24 @@
     }
   },
   "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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\\n\\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\\n    Returns:\\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"}' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {{- tool_call.arguments|tojson }}\n            {%- endif %}\n            {{- '\\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if not message.name is defined %}\n            {{- raise_exception(\"Tool response dicts require a 'name' key indicating the name of the called function!\") }}\n        {%- endif %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\\n' }}\n        {%- endif %}\n        {{- '<tool_response>\\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\\n</tool_response>\\n' }}\n        {%- else %}\n            {{- '\\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+    }
+  ],
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizer"
 }