Sync llama : Support llama 4 text-only

Author: JamePeng

llama_cpp/llama_chat_format.py

@@ -53,6 +53,11 @@
 # Source: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/blob/main/tokenizer_config.json
 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|>"
+
 ### Chat Completion Handler ###
 
 
@@ -1035,6 +1040,25 @@ def format_llama3(
     return ChatFormatterResponse(prompt=_prompt, stop=_sep)
 
 
+# Chat format for Llama-4 models text only, see more details at:
+# https://github.com/meta-llama/llama-models/blob/main/models/llama4/chat_format.py#L61-L316
+@register_chat_format("llama-4")
+def format_llama4(
+    messages: List[llama_types.ChatCompletionRequestMessage],
+    **kwargs: Any,
+) -> ChatFormatterResponse:
+    _roles = dict(
+        system="<|header_start|>system<|header_end|>\n\n",
+        user="<|header_start|>user<|header_end|>\n\n",
+        assistant="<|header_start|>assistant<|header_end|>\n\n",
+    )
+    _sep = "<|eot|>"
+    _messages = _map_roles(messages, _roles)
+    _messages.append((_roles["assistant"], None))
+    _prompt = _format_no_colon_single("", _messages, _sep)
+    return ChatFormatterResponse(prompt=_prompt, stop=_sep)
+
+
 @register_chat_format("alpaca")
 def format_alpaca(
     messages: List[llama_types.ChatCompletionRequestMessage],

llama_cpp/llama_cpp.py

@@ -241,6 +241,7 @@
 #     LLAMA_VOCAB_PRE_TYPE_SUPERBPE       = 30,
 #     LLAMA_VOCAB_PRE_TYPE_TRILLION       = 31,
 #     LLAMA_VOCAB_PRE_TYPE_BAILINGMOE     = 32,
+#     LLAMA_VOCAB_PRE_TYPE_LLAMA4         = 33,
 # };
 LLAMA_VOCAB_PRE_TYPE_DEFAULT = 0
 LLAMA_VOCAB_PRE_TYPE_LLAMA3 = 1
@@ -275,6 +276,7 @@
 LLAMA_VOCAB_PRE_TYPE_SUPERBPE = 30
 LLAMA_VOCAB_PRE_TYPE_TRILLION = 31
 LLAMA_VOCAB_PRE_TYPE_BAILINGMOE = 32
+LLAMA_VOCAB_PRE_TYPE_LLAMA4 = 33
 
 
 # // note: these values should be synchronized with ggml_rope