llama_chat_format: Add Gemma3ChatHandler for gemma3 multimodel support

Author: JamePeng

llama_cpp/llama_chat_format.py

@@ -57,9 +57,10 @@
 LLAMA3_INSTRUCT_CHAT_TEMPLATE = "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
 
 # Source: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct/blob/main/tokenizer_config.json
-LLAMA4_INSTRUCT_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"
 LLAMA4_INSTRUCT_BOS_TOKEN = "<|begin_of_text|>"
 LLAMA4_INSTRUCT_EOS_TOKEN = "<|eot|>"
+LLAMA4_INSTRUCT_CHAT_TEMPLATE = "{% 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"
+
 
 # Source: https://huggingface.co/openai/gpt-oss-20b/blob/main/tokenizer_config.json
 GPT_OSS_BOS_TOKEN = "<|startoftext|>"
@@ -3570,6 +3571,65 @@ class MiniCPMv26ChatHandler(Llava15ChatHandler):
     )
 
 
+class Gemma3ChatHandler(Llava15ChatHandler):
+    DEFAULT_SYSTEM_MESSAGE = "You are a helpful assistant."
+
+    GEMMA3_BOI_TOKEN  = "<start_of_image>"
+    GEMMA3_EOI_TOKEN = "<end_of_image>"
+    GEMMA3_BOS_TOKEN = "<bos>"
+    GEMMA3_EOS_TOKEN = "<eos>"
+
+    CHAT_FORMAT = (
+        "{% if messages[0]['role'] == 'system' %}"
+        "{% set loop_messages = messages[1:] %}"
+        "{% if messages[0]['content'] is string %}"
+        "{% set first_user_prefix = messages[0]['content'] + '\n\n' %}"
+        "{% else %}"
+        "{% set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' %}"
+        "{% endif %}"
+        "{% else %}"
+        "{% set loop_messages = messages %}"
+        "{% set first_user_prefix = '' %}"
+        "{% endif %}"
+
+        "{% for message in loop_messages %}"
+        "{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}"
+        "{{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}"
+        "{% endif %}"
+
+        "{% if message['role'] == 'assistant' %}"
+        "{% set role = 'model' %}"
+        "{% else %}"
+        "{% set role = message['role'] %}"
+        "{% endif %}"
+
+        "{{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else '') }}"
+
+        "{% if message['content'] is string %}"
+        "{{ message['content'] | trim }}"
+        "{% elif message['content'] is iterable %}"
+        "{% for item in message['content'] %}"
+        "{% if item['type'] == 'image_url' and item['image_url'] is string %}"
+        "{{ '<start_of_image>' + item['image_url'] + '<end_of_image>' }}"
+        "{% elif item['type'] == 'image_url' and item['image_url'] is mapping %}"
+        "{{ '<start_of_image>' + item['image_url']['url'] + '<end_of_image>' }}"
+        "{% elif item['type'] == 'text' %}"
+        "{{ item['text'] | trim }}"
+        "{% endif %}"
+        "{% endfor %}"
+        "{% else %}"
+        "{{ raise_exception('Invalid content type') }}"
+        "{% endif %}"
+
+        "<end_of_turn>\n"
+        "{% endfor %}"
+
+        "{% if add_generation_prompt %}"
+        "<start_of_turn>model\n"
+        "{% endif %}"
+    )
+
+
 class Qwen25VLChatHandler(Llava15ChatHandler):
     DEFAULT_SYSTEM_MESSAGE = "You are a helpful assistant."