simmo commited on
Commit
5748ffb
1 Parent(s): 1af473e

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -2050,7 +2050,7 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{{- if .Suffix }}<|fim_begin|>{{ .Prompt }}<|fim_hole|>{{ .Suffix }}<|fim_end|>\n{{- else }}{#- 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{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n{%- for message in messages %}\n{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}\n{%- endfor %}\n{%- if add_generation_prompt %}\n{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}{{- end }}\n",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- if .Suffix }}<|fim_begin|>{{ .Prompt }}<|fim_hole|>{{ .Suffix }}<|fim_end|>\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{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n{%- for message in messages %}\n{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}\n{%- endfor %}\n{%- if add_generation_prompt %}\n{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [