Upload tokenizer

tokenizer_config.json

@@ -2051,7 +2051,7 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "chat_template": "\n        {{- bos_token }}\n        {%- if custom_tools is defined %}\n            {%- set tools = custom_tools %}\n        {%- endif %}\n        {%- if not tools_in_user_message is defined %}\n            {%- set tools_in_user_message = true %}\n        {%- endif %}\n        {%- if not date_string is defined %}\n            {%- if strftime_now is defined %}\n                {%- set date_string = strftime_now(\"%d %b %Y\") %}\n            {%- else %}\n                {%- set date_string = \"07 Dec 2024\" %}\n            {%- endif %}\n        {%- endif %}\n        {%- if not tools is defined %}\n            {%- set tools = none %}\n        {%- endif %}\n        {#- Extract system message #}\n        {%- if messages[0]['role'] == 'system' %}\n            {%- set system_message = messages[0]['content']|trim %}\n            {%- set messages = messages[1:] %}\n        {%- else %}\n            {%- set system_message = \"\" %}\n        {%- endif %}\n        {#- System message #}\n        {{- \"<|start_header_id|>system<|end_header_id|>\" }}\n        {{- \"Cutting Knowledge Date: December 2023\" }}\n        {{- \"Today Date: \" + date_string + \"\" }}\n        {%- if tools is not none and not tools_in_user_message %}\n            {{- \"Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.\n        \" }}\n            {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n            {{- \"Do not use variables.\" }}\n            {%- for t in tools %}\n                {{- {\"name\": t.name, \"description\": t.description, \"parameters\": t.parameters.properties} | tojson(indent=4) }}\n                {{- \"\" }}\n            {%- endfor %}\n        {%- endif %}\n        {{- system_message }}\n        {{- \"<|eot_id|>\" }}\n        {%- if tools_in_user_message and not tools is none %}\n            {%- if messages | length != 0 %}\n                {%- set first_user_message = messages[0]['content']|trim %}\n                {%- set messages = messages[1:] %}\n            {%- else %}\n                {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n        {%- endif %}\n            {{- '<|start_header_id|>user<|end_header_id|>' -}}\n            {{- \"Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.\" }}\n            {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n            {{- \"Do not use variables.\" }}\n            {%- for t in tools %}\n                {{- {\"name\": t.name, \"description\": t.description, \"parameters\": t.parameters.properties} | tojson(indent=4) }}\n                {{- \"\" }}\n            {%- endfor %}\n            {{- first_user_message + \"<|eot_id|>\"}}\n        {%- endif %}\n        {%- for message in messages %}\n            {%- if not (message.role == 'tool' or 'tool_calls' in message) %}\n                {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + message['content'] | trim + '<|eot_id|>' }}\n            {%- elif 'tool_calls' in message %}\n                {%- if not message.tool_calls|length == 1 %}\n                    {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n                {%- endif %}\n                {%- set tool_call = message.tool_calls[0].function %}\n                {{- '<|start_header_id|>assistant<|end_header_id|>' -}}\n                {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n                {{- '\"parameters\": ' }}\n                {{- tool_call.arguments | tojson }}\n                {{- \"}\" }}\n                {{- \"<|eot_id|>\" }}\n            {%- endif %}\n        {%- endfor %}\n        {%- if add_generation_prompt %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>' }}\n        {%- endif %}\n        ",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
@@ -2061,5 +2061,5 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|reserved_special_token_0|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizer"
 }