Upload tokenizer
Browse files- tokenizer_config.json +1 -1
 
    	
        tokenizer_config.json
    CHANGED
    
    | 
         @@ -2050,7 +2050,7 @@ 
     | 
|
| 2050 | 
         
             
                }
         
     | 
| 2051 | 
         
             
              },
         
     | 
| 2052 | 
         
             
              "bos_token": "<|begin_of_text|>",
         
     | 
| 2053 | 
         
            -
              "chat_template": "{%- set loop_messages = messages -%}\n{%- set message_roles = ['system', 'user', 'assistant', 'tool'] -%}\n{%- set system_prompt_suffix -%}\n{%- filter trim -%}\nIn addition to plain text responses, you can chose to call one or more of the provided functions.\n\nUse the following rule to decide when to call a function:\n  * if the response can be generated from your internal knowledge (e.g., as in the case of queries like \"What is the capital of Poland?\"), do so\n  * if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls\n\nIf you decide to call functions:\n  * prefix function calls with functools marker (no closing marker required)\n  * all function calls should be generated in a single JSON list formatted as functools[{\"name\": [function name], \"arguments\": [function arguments as JSON]}, ...]\n  * follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples\n  * respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0\n  * make sure you pick the right functions that match the user intent\n\nAvailable functions as JSON spec:\n{%- endfilter -%}\n{%- endset -%}\n{%- set system_prompt_suffix = system_prompt_suffix + \"\\n\" + functions -%}\n{%- set system_prompt_suffix = system_prompt_suffix + '\\nToday is ' + datetime 
     | 
| 2054 | 
         
             
              "clean_up_tokenization_spaces": true,
         
     | 
| 2055 | 
         
             
              "eos_token": "<|end_of_text|>",
         
     | 
| 2056 | 
         
             
              "legacy": false,
         
     | 
| 
         | 
|
| 2050 | 
         
             
                }
         
     | 
| 2051 | 
         
             
              },
         
     | 
| 2052 | 
         
             
              "bos_token": "<|begin_of_text|>",
         
     | 
| 2053 | 
         
            +
              "chat_template": "{%- set loop_messages = messages -%}\n{%- set message_roles = ['system', 'user', 'assistant', 'tool'] -%}\n{%- set system_prompt_suffix -%}\n{%- filter trim -%}\nIn addition to plain text responses, you can chose to call one or more of the provided functions.\n\nUse the following rule to decide when to call a function:\n  * if the response can be generated from your internal knowledge (e.g., as in the case of queries like \"What is the capital of Poland?\"), do so\n  * if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls\n\nIf you decide to call functions:\n  * prefix function calls with functools marker (no closing marker required)\n  * all function calls should be generated in a single JSON list formatted as functools[{\"name\": [function name], \"arguments\": [function arguments as JSON]}, ...]\n  * follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples\n  * respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0\n  * make sure you pick the right functions that match the user intent\n\nAvailable functions as JSON spec:\n{%- endfilter -%}\n{%- endset -%}\n{%- set system_prompt_suffix = system_prompt_suffix + \"\\n\" + functions -%}\n{%- set system_prompt_suffix = system_prompt_suffix + '\\nToday is ' + datetime + '.' -%}\n{%- set ns = namespace(role='', content='') -%}\n{#- Basic consistency checks -#}\n{%- if not loop_messages -%}\n  {{ raise_exception('Expected non-empty messages') }}\n{%- endif -%}\n{%- for message in loop_messages -%}\n  {%- set ns.role = message['role'] | lower -%}\n  {%- if ns.role not in message_roles -%}\n    {{ raise_exception('Invalid role ' + message['role'] + '. Only ' + message_roles + ' are supported.') }}\n  {%- endif -%}\n  {%- set msg_content = message['content'] | default('', true) | trim -%}\n  {%- if loop.index0 == 0 -%}\n    {%- if ns.role == 'system' -%}\n      {%- set system_prompt = '<|start_header_id|>' + 'system' + '<|end_header_id|>\\n\\n' + message['content'] | trim + '\\n' + system_prompt_suffix + '<|eot_id|>' -%}\n    {%- else -%}\n      {%- set system_prompt = '<|start_header_id|>' + 'system' + '<|end_header_id|>\\n\\nYou are a helpful assistant with access to functions.\\n' + system_prompt_suffix + '<|eot_id|>' -%}\n    {%- endif -%}\n    {%- set ns.content = bos_token + system_prompt -%}\n    {{- ns.content -}}\n  {%- endif -%}\n  {%- if loop.index0 > 0 or ns.role != 'system' -%}\n    {%- set ns.content = '<|start_header_id|>' + ns.role + '<|end_header_id|>\\n\\n' + msg_content -%}\n    {%- if 'tool_calls' in message and message['tool_calls'] -%}\n      {%- set tool = namespace(calls=[]) -%}\n      {%- for call in message['tool_calls'] -%}\n        {%- set tool.calls = tool.calls + ['{\"name\": \"' + call['function']['name'] + '\", \"arguments\": ' + call['function']['arguments'] + '}'] -%}\n      {%- endfor -%}\n      {%- set ns.content = ns.content + ' functools[' + tool.calls | join(', ') + ']' -%}\n    {%- endif -%}\n    {%- set ns.content = ns.content + '<|eot_id|>' -%}\n    {{- ns.content -}}\n  {%- endif -%}\n{%- endfor -%}\n{{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n",
         
     | 
| 2054 | 
         
             
              "clean_up_tokenization_spaces": true,
         
     | 
| 2055 | 
         
             
              "eos_token": "<|end_of_text|>",
         
     | 
| 2056 | 
         
             
              "legacy": false,
         
     |