Upload folder using huggingface_hub

chat_template.jinja

@@ -1,51 +1,79 @@
 {{- bos_token }}
-{%- if custom_tools is defined and custom_tools%}
+{%- if custom_tools is defined %}
     {%- set tools = custom_tools %}
 {%- endif %}
-{%- if tools is defined and tools %}
-    {%- set tool_definition = (tool_definition|string) + ((tools | tojson(indent=4))|string) %}
-{%- else %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
     {%- set tools = none %}
 {%- endif %}
 
-
 {#- This block extracts the system message, so we can slot it into the right place. #}
-{%- if messages[0]['role'] == 'system' %}
-    {%- set user_provided_system_message = true %}
+{%- if messages[0]['role'] == 'system' %}    
     {%- if messages[0]['content'] is string %}
         {%- set system_message = messages[0]['content']|trim %}
     {%- else %}
+        {#- FIXME: The processor requires an array, always. #}
         {%- set system_message = messages[0]['content'][0]['text']|trim %}
     {%- endif %}
     {%- set messages = messages[1:] %}
+    {%- set user_supplied_system_message = true %}
 {%- else %}
-    {%- if tools is not none  %}
-        {#- Since not system_message was provided by user, if tool is provided, system_message is now default tool system message #}
-        {#- This system message is from llama website:https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/  #}
-        {%- set system_message = "You are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n" %}
-    {%- else %}
-        {%- set system_message = "" %}
-    {%- endif %}
+    {%- set system_message = "" %}
+    {%- set user_supplied_system_message = false %}
 {%- endif %}
-{#- Now writing the system message: use the user provided system message if user_provided_system_message, else default tool system message if tools presented #}
-{%- if system_message %}
-    {#- always use user provided system message to override default tool system message #}
+
+{#- System message if the user supplied one #}
+{%- if user_supplied_system_message %}
     {{- "<|header_start|>system<|header_end|>\n\n" }}
-    {{- system_message }}
-    {%- if user_provided_system_message and tools %}
-        {{- "\nHere is a list of functions in JSON format that you can invoke. Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\n" }}
-        {{- tool_definition -}}
-        {%- elif tool_definition %}
-        {{- tool_definition -}}
+    {%- if tools is not none %}
+        {{- "Environment: ipython\n" }}
     {%- endif %}
+    {%- if tools is not none and not tools_in_user_message %}
+        {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+        {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+        {{- "Do not use variables.\n\n" }}
+        {%- for t in tools %}
+            {{- t | tojson(indent=4) }}
+            {{- "\n\n" }}
+        {%- endfor %}
+    {%- endif %}
+    {{- system_message }}
     {{- "<|eot|>" }}
 {%- endif %}
 
-{#- Now deal with all other messages #}
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|header_start|>user<|header_end|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot|>"}}
+{%- endif %}
+
 {%- for message in messages %}
-    {#- Base case: messages that are not from tool role and has empty tool_call list  #}
-    {%- if not (message.role == 'ipython' or message.role == 'tool' or ('tool_calls' in message and  message.tool_calls|length != 0 )) %}
-        {{- '<|header_start|>' + message['role'] + '<|header_end|>\n\n' }}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+    {{- '<|header_start|>' + message['role'] + '<|header_end|>\n\n' }}
         {%- if message['content'] is string %}
             {{- message['content'] }}
         {%- else %}
@@ -53,16 +81,14 @@
                 {%- if content['type'] == 'image' %}
                     {{- '<|image|>' }}
                 {%- elif content['type'] == 'text' %}
-                    {{- content['text'] | trim }}
+                    {{- content['text'] }}
                 {%- endif %}
             {%- endfor %}
         {%- endif %}
-    {{- "<|eot|>" }}
-    {#- Tool case: messages has non-empty tool_call list, must from assistant #}
-    {%- elif 'tool_calls' in message %}
-        {#- assume tool_calls are always coming from assistant #}
-        {%- if message.role == 'assistant' %}
-            {{- '<|header_start|>assistant<|header_end|>\n\n' -}}
+        {{- "<|eot|>" }}
+    {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}
+       {{- '<|header_start|>assistant<|header_end|>\n\n' -}}
+       {{- '<|python_start|>' }}
         {%- if message['content'] is string %}
             {{- message['content'] }}
         {%- else %}
@@ -74,38 +100,24 @@
                 {%- endif %}
             {%- endfor %}
         {%- endif %}
-            {{- "[" }}
+       {{- '<|python_end|>' }}
         {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-                {{-  tool_call.name + '(' -}}
-            {%- for param in tool_call.arguments %}
-                {{- param + '="' -}}
-                {{- "%s" | format(tool_call.arguments[param]) -}}
-                {{- '"' -}}
-                {% if not loop.last %}, {% endif %}
-            {%- endfor %}
-            {{- ')' -}}
-            {% if not loop.last %}, {% endif %}
+           {{- '{"name": "' + tool_call.function.name + '", ' }}
+           {{- '"parameters": ' }}
+           {{- tool_call.function.arguments | tojson }}
+           {{- "}" }}
         {%- endfor %}
-        {{- "]<|eot|>" }}
-{%- endif %}
-{#- Tool_response case: messages are from tool_response  #}
+       {{- "<|eot|>" }}
     {%- elif message.role == "tool" or message.role == "ipython" %}
         {{- "<|header_start|>ipython<|header_end|>\n\n" }}
-        {%- if message.content is string %}
-            {{-  message.content  | tojson }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
         {%- else %}
-            {%- for content in message['content']  %}
-                {%- if content['type']  == 'text' %}
-                    {{-  content['text'] | tojson }}
-                {%- endif %}
-            {%- endfor %}
+            {{- message.content }}
         {%- endif %}
         {{- "<|eot|>" }}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|header_start|>assistant<|header_end|>\n\n' }}
-{%- endif %}
+{%- endif %}

tokenizer_config.json

@@ -9096,5 +9096,5 @@
   "processor_class": "Llama4Processor",
   "tokenizer_class": "PreTrainedTokenizer",
   "unk_token": null,
-  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined and custom_tools%}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if tools is defined and tools %}\n    {%- set tool_definition = tool_definition ~ (tools | tojson(indent=4)) %}\n{%- else %}\n    {%- set tools = none %}\n{%- endif %}\n\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set user_provided_system_message = true %}\n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content']|trim %}\n    {%- else %}\n        {%- set system_message = messages[0]['content'][0]['text']|trim %}\n    {%- endif %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- if tools is not none  %}\n        {#- Since not system_message was provided by user, if tool is provided, system_message is now default tool system message #}\n        {#- This system message is from llama website:https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/  #}\n        {%- set system_message = \"You are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\\n\\n1. FUNCTION CALLS:\\n- ONLY use functions that are EXPLICITLY listed in the function list below\\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \\\"I don't have access to [Unavailable service] information\\\"\\n- If a function is not in the list, respond ONLY with internal knowledge or \\\"I don't have access to [Unavailable service] information\\\"\\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\\nExamples:\\nCORRECT: [get_weather(location=\\\"Vancouver\\\"), calculate_route(start=\\\"Boston\\\", end=\\\"New York\\\")] <- Only if get_weather and calculate_route are in function list\\nINCORRECT: get_weather(location=\\\"New York\\\")\\nINCORRECT: Let me check the weather: [get_weather(location=\\\"New York\\\")]\\nINCORRECT: [get_events(location=\\\"Singapore\\\")] <- If function not in list\\n\\n2. RESPONSE RULES:\\n- For pure function requests matching a listed function: ONLY output the function call(s)\\n- For knowledge questions: ONLY output text\\n- For missing parameters: ONLY request the specific missing parameters\\n- For unavailable services (not in function list): output ONLY with internal knowledge or \\\"I don't have access to [Unavailable service] information\\\". Do NOT execute a function call.\\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\\n- NEVER combine text and function calls in the same response\\n- NEVER suggest alternative functions when the requested service is unavailable\\n- NEVER create or invent new functions not listed below\\n\\n3. STRICT BOUNDARIES:\\n- ONLY use functions from the list below - no exceptions\\n- NEVER use a function as an alternative to unavailable information\\n- NEVER call functions not present in the function list\\n- NEVER add explanatory text to function calls\\n- NEVER respond with empty brackets\\n- Use proper Python/JSON syntax for function calls\\n- Check the function list carefully before responding\\n\\n4. TOOL RESPONSE HANDLING:\\n- When receiving tool responses: provide concise, natural language responses\\n- Don't repeat tool response verbatim\\n- Don't add supplementary information\\n\\nHere is a list of functions in JSON format that you can invoke:\\n\" %}\n    {%- else %}\n        {%- set system_message = \"\" %}\n    {%- endif %}\n{%- endif %}\n{#- Now writing the system message: use the user provided system message if user_provided_system_message, else default tool system message if tools presented #}\n{%- if system_message %}\n    {#- always use user provided system message to override default tool system message #}\n    {{- \"<|header_start|>system<|header_end|>\\n\\n\" }}\n    {{- system_message }}\n    {%- if user_provided_system_message and tools %}\n        {{- \"\\nHere is a list of functions in JSON format that you can invoke. Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\\n\" }}\n        {{- tool_definition -}}\n        {%- elif tool_definition %}\n        {{- tool_definition -}}\n    {%- endif %}\n    {{- \"<|eot|>\" }}\n{%- endif %}\n\n{#- Now deal with all other messages #}\n{%- for message in messages %}\n    {#- Base case: messages that are not from tool role and has empty tool_call list  #}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or ('tool_calls' in message and  message.tool_calls|length != 0 )) %}\n        {{- '<|header_start|>' + message['role'] + '<|header_end|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] | trim }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n    {{- \"<|eot|>\" }}\n    {#- Tool case: messages has non-empty tool_call list, must from assistant #}\n    {%- elif 'tool_calls' in message %}\n        {#- assume tool_calls are always coming from assistant #}\n        {%- if message.role == 'assistant' %}\n            {{- '<|header_start|>assistant<|header_end|>\\n\\n' -}}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n            {{- \"[\" }}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n                {{-  tool_call.name + '(' -}}\n            {%- for param in tool_call.arguments %}\n                {{- param + '=\"' -}}\n                {{- \"%s\" | format(tool_call.arguments[param]) -}}\n                {{- '\"' -}}\n                {% if not loop.last %}, {% endif %}\n            {%- endfor %}\n            {{- ')' -}}\n            {% if not loop.last %}, {% endif %}\n        {%- endfor %}\n        {{- \"]<|eot|>\" }}\n{%- endif %}\n{#- Tool_response case: messages are from tool_response  #}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|header_start|>ipython<|header_end|>\\n\\n\" }}\n        {%- if message.content is string %}\n            {{-  message.content  | tojson }}\n        {%- else %}\n            {%- for content in message['content']  %}\n                {%- if content['type']  == 'text' %}\n                    {{-  content['text'] | tojson }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|header_start|>assistant<|header_end|>\\n\\n' }}\n{%- endif %}"
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}    \n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content']|trim %}\n    {%- else %}\n        {#- FIXME: The processor requires an array, always. #}\n        {%- set system_message = messages[0]['content'][0]['text']|trim %}\n    {%- endif %}\n    {%- set messages = messages[1:] %}\n    {%- set user_supplied_system_message = true %}\n{%- else %}\n    {%- set system_message = \"\" %}\n    {%- set user_supplied_system_message = false %}\n{%- endif %}\n\n{#- System message if the user supplied one #}\n{%- if user_supplied_system_message %}\n    {{- \"<|header_start|>system<|header_end|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|header_start|>user<|header_end|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|header_start|>' + message['role'] + '<|header_end|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}\n       {{- '<|header_start|>assistant<|header_end|>\\n\\n' -}}\n       {{- '<|python_start|>' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n       {{- '<|python_end|>' }}\n        {%- for tool_call in message.tool_calls %}\n           {{- '{\"name\": \"' + tool_call.function.name + '\", ' }}\n           {{- '\"parameters\": ' }}\n           {{- tool_call.function.arguments | tojson }}\n           {{- \"}\" }}\n        {%- endfor %}\n       {{- \"<|eot|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|header_start|>ipython<|header_end|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|header_start|>assistant<|header_end|>\\n\\n' }}\n{%- endif %}\n"
 }