Upload tokenizer

chat_template.jinja

@@ -0,0 +1,45 @@
+{%- if tools %}
+{{- '<|system|>\n' }}
+{%- if messages[0]['role'] == 'system' %}
+{{- messages[0]['content'] }}
+{%- set remaining_messages = messages[1:] %}
+{%- else %}
+{%- set remaining_messages = messages %}
+{%- endif %}
+{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\n\n# Tools\n\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\n\n<tools>' + tools|tojson(indent=2) + '</tools>\n\n# Output Format\n\nYour response MUST follow this format when making function calls:\n<tool_call>\n[\n  {"name": "function_name", "arguments": {"arg1": "value1", "arg2": "value2"}},\n  {"name": "another_function", "arguments": {"arg": "value"}}\n]\n</tool_call>\nIf no function calls are needed, respond normally without the tool_call tags.\n' }}
+{%- for message in remaining_messages %}
+{%- if message['role'] == 'user' %}
+{{- '<|user|>\n' + message['content'] + '\n' }}
+{%- elif message['role'] == 'assistant' %}
+{%- if message.content %}
+{{- '<|assistant|>\n' + message['content'] }}
+{%- endif %}
+{%- if message.tool_calls %}
+{{- '\n<tool_call>\n' }}
+{{- message.tool_calls|tojson(indent=2) }}
+{{- '\n</tool_call>' }}
+{%- endif %}
+{{- eos_token + '\n' }}
+{%- elif message['role'] == 'tool' %}
+{{- '<|assistant|>\n<tool_response>\n' + message['content'] + '\n</tool_response>\n' }}
+{%- endif %}
+{%- endfor %}
+{{- '<|assistant|>\n' if add_generation_prompt }}
+{%- else %}
+{%- for message in messages %}
+{%- if message['role'] == 'system' %}
+{{- '<|system|>\n' + message['content'] + '\n' }}
+{%- elif message['role'] == 'user' %}
+{{- '<|user|>\n' + message['content'] + '\n' }}
+{%- elif message['role'] == 'assistant' %}
+{%- if not loop.last %}
+{{- '<|assistant|>\n' + message['content'] + eos_token + '\n' }}
+{%- else %}
+{{- '<|assistant|>\n' + message['content'] + eos_token }}
+{%- endif %}
+{%- endif %}
+{%- if loop.last and add_generation_prompt %}
+{{- '<|assistant|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- endif %}

tokenizer_config.json

@@ -16219,7 +16219,6 @@
     ">>PASSWORD<<",
     ">>KEY<<"
   ],
-  "chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n  {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n  {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},