Upload tokenizer
Browse files- .gitattributes +1 -0
- chat_template.jinja +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
    	
        .gitattributes
    CHANGED
    
    | @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text | |
| 33 | 
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         | 
| 34 | 
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         | 
| 35 | 
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         | 
|  | 
|  | |
| 33 | 
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         | 
| 34 | 
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         | 
| 35 | 
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         | 
| 36 | 
            +
            tokenizer.json filter=lfs diff=lfs merge=lfs -text
         | 
    	
        chat_template.jinja
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            {% 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 %}
         | 
    	
        tokenizer.json
    CHANGED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        tokenizer_config.json
    CHANGED
    
    | @@ -181,14 +181,14 @@ | |
| 181 | 
             
                }
         | 
| 182 | 
             
              },
         | 
| 183 | 
             
              "bos_token": "<|begin▁of▁sentence|>",
         | 
| 184 | 
            -
              "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 %}",
         | 
| 185 | 
             
              "clean_up_tokenization_spaces": false,
         | 
| 186 | 
             
              "eos_token": "<|end▁of▁sentence|>",
         | 
|  | |
| 187 | 
             
              "legacy": true,
         | 
| 188 | 
             
              "model_max_length": 16384,
         | 
| 189 | 
             
              "pad_token": "<|end▁of▁sentence|>",
         | 
| 190 | 
             
              "sp_model_kwargs": {},
         | 
| 191 | 
            -
              "tokenizer_class": " | 
| 192 | 
             
              "unk_token": null,
         | 
| 193 | 
             
              "use_default_system_prompt": false
         | 
| 194 | 
             
            }
         | 
|  | |
| 181 | 
             
                }
         | 
| 182 | 
             
              },
         | 
| 183 | 
             
              "bos_token": "<|begin▁of▁sentence|>",
         | 
|  | |
| 184 | 
             
              "clean_up_tokenization_spaces": false,
         | 
| 185 | 
             
              "eos_token": "<|end▁of▁sentence|>",
         | 
| 186 | 
            +
              "extra_special_tokens": {},
         | 
| 187 | 
             
              "legacy": true,
         | 
| 188 | 
             
              "model_max_length": 16384,
         | 
| 189 | 
             
              "pad_token": "<|end▁of▁sentence|>",
         | 
| 190 | 
             
              "sp_model_kwargs": {},
         | 
| 191 | 
            +
              "tokenizer_class": "LlamaTokenizerFast",
         | 
| 192 | 
             
              "unk_token": null,
         | 
| 193 | 
             
              "use_default_system_prompt": false
         | 
| 194 | 
             
            }
         |