Add tokenizer_config.json to root for TGI compatibility

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>"
+  ],
+  "is_local": false,
+  "model_max_length": 128000,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend",
+  "chat_template": "[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{{ tool | tojson(ensure_ascii=False) }}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro visible_text(content) -%}\n    {%- if content is string -%}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping -%}\n        {%- for item in content -%}\n            {%- if item is mapping and item.type == 'text' -%}\n                {{- item.text }}\n            {%- elif item is string -%}\n                {{- item }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{- content }}\n    {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in messages %}\n    {%- if m.role == 'user' %}\n        {% set ns.last_user_index = loop.index0 -%}\n    {%- endif %}\n{%- endfor %}\n{% for m in messages %}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set reasoning_content = '' %}\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n    {%- set reasoning_content = m.reasoning_content %}\n{%- else %}\n    {%- if '</think>' in content %}\n        {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n        {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n    {%- endif %}\n{%- endif %}\n{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}\n{{ '<think>' + reasoning_content.strip() +  '</think>'}}\n{%- else -%}\n{{ '</think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n    {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if m.content is string -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n    {{- '<|observation|>' }}\n{%- endif %}\n{{- '<tool_response>' }}\n{{- m.content }}\n{{- '</tool_response>' }}\n{%- else -%}\n<|observation|>{% for tr in m.content %}\n<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}\n{%- endif -%}"
+}