mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
* port upstream https://github.com/ggml-org/llama.cpp/pull/16932 * Add fixed chat templates. * fix grammar when tool have no argument * Insert additional stops for Kimi-K2 * Fix `no triggers set for lazy grammar!` for GLM4.5/4.6 * update chat.cpp * fix grammar for GLM 4.5/4.6 * chat: Fix streaming parser for granite models (#15682) * fix(chat): fix streaming parser for granite models * tests: add test cases for Granite models chat parser * common : Fix corrupted memory error on json grammar initialization (#16038) Initalizing RESERVED_NAME in is_reserved_name() is not thread safe and leads to corrupted memory when used from multiple threads as can be seen in the asan trace below. This fixes the initialization to make it thread-safe. #0 0x000100abd018 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) __hash_table:1565 #1 0x000100ab0320 in SchemaConverter::visit(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) json-schema-to-grammar.cpp:802 #2 0x000100aafc48 in std::__1::__function::__func<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2, std::__1::allocator<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> (std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319 #3 0x000100a2c938 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&), std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>, void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319 #4 0x000100a139f8 in foreach_function(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::function<void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)> const&) chat.cpp:762 #5 0x000100a2a7f4 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0, std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0>, void (common_grammar_builder const&)>::operator()(common_grammar_builder const&) function.h:319 #6 0x000100aa98f4 in build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&) json-schema-to-grammar.cpp:982 #7 0x0001009c9314 in common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool) chat.cpp:1110 #8 0x0001009b8afc in common_chat_templates_apply_jinja(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:1992 #9 0x0001009b533c in common_chat_templates_apply(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:2074 #10 0x000100810120 in llamacpp_apply_chat_template+0x724 (predict_oai-98384e17fb94e863:arm64+0x100090120) ... ==45482==Register values: x[0] = 0x00006020004147f8 x[1] = 0x00006080000013c8 x[2] = 0x0000000000000000 x[3] = 0x0000604006289738 x[4] = 0x0000000000000002 x[5] = 0x0000000000000001 x[6] = 0x04034000004b4000 x[7] = 0x0000000000000001 x[8] = 0xbebebebebebebebe x[9] = 0x17d7d7d7d7d7d7d7 x[10] = 0x00000c04000828ff x[11] = 0x0000000000000001 x[12] = 0x000000002018d383 x[13] = 0x0000000000000000 x[14] = 0xfa0000000000fafa x[15] = 0x000010700001ffff x[16] = 0x000000019dc012c0 x[17] = 0x00000001021284f8 x[18] = 0x0000000000000000 x[19] = 0x00000001700acdc0 x[20] = 0x0000000000000002 x[21] = 0x000000002018d384 x[22] = 0x16dd16fd2e731151 x[23] = 0x0000007000020000 x[24] = 0x0000000100c69c08 x[25] = 0x0000000100c69c20 x[26] = 0x00006080000013c7 x[27] = 0x0000000100c69c00 x[28] = 0x00000001700acd60 fp = 0x00000001700aceb0 lr = 0x0000000100abce30 sp = 0x00000001700acd60 AddressSanitizer can not provide additional info. SUMMARY: AddressSanitizer: SEGV __hash_table:1565 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) Thread T5 created by T0 here: #0 0x0001020b99d4 in pthread_create+0x5c (libclang_rt.asan_osx_dynamic.dylib:arm64e+0x359d4) #1 0x000100873910 in std::sys::pal::unix:🧵:Thread:🆕:h77254fdd87a28e05+0x118 (predict_oai-98384e17fb94e863:arm64+0x1000f3910) #2 0x0001007c7a1c in test::run_test::haeb3c2bcd5ed6cf6+0x76c (predict_oai-98384e17fb94e863:arm64+0x100047a1c) #3 0x0001007aedb0 in test::console::run_tests_console::he9d142d704f3a986+0x149c (predict_oai-98384e17fb94e863:arm64+0x10002edb0) #4 0x0001007c5758 in test::test_main::hf86a5e20735245b9+0x118 (predict_oai-98384e17fb94e863:arm64+0x100045758) #5 0x0001007c5da0 in test::test_main_static::h61ee9c8fd30abca0+0x54 (predict_oai-98384e17fb94e863:arm64+0x100045da0) ... ==45482==ABORTING * common : fix reasoning before forced tool call via tool_choice = required (#16264) * common : fix reasoning before forced tool call via tool_choice = required * common : improve reasoning and commentary handling when tool_choice is required (cherry picked from commit c746984956d6882c2de73d53ae2bb3bdf889e475) --------- Co-authored-by: Alde Rojas <hello@alde.dev> * Try fix Jinja template for GLM * Improve Kimi-K2 chat template * Fix "Invalid tool call arguments passed" in a rare case. In a rare case, the model may emit a raw string that begins with a valid JSON string. This commit adds unit tests to cover that scenario and fixes the regression introduced during the Kimi-K2 adaptation. --------- Co-authored-by: shun095 <8069181+shun095@users.noreply.github.com> Co-authored-by: David Ribeiro Alves <davidralves@gmail.com> Co-authored-by: crat0z <11581854+crat0z@users.noreply.github.com> Co-authored-by: Alde Rojas <hello@alde.dev>
118 lines
6.1 KiB
Django/Jinja
118 lines
6.1 KiB
Django/Jinja
{% macro render_extra_keys(json_dict, handled_keys) %}
|
|
{%- if json_dict is mapping %}
|
|
{%- for json_key in json_dict if json_key not in handled_keys %}
|
|
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
|
|
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
|
{%- else %}
|
|
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
|
{%- endif %}
|
|
{%- endfor %}
|
|
{%- endif %}
|
|
{% endmacro %}
|
|
|
|
{%- if messages[0]["role"] == "system" %}
|
|
{%- set system_message = messages[0]["content"] %}
|
|
{%- set loop_messages = messages[1:] %}
|
|
{%- else %}
|
|
{%- set loop_messages = messages %}
|
|
{%- endif %}
|
|
|
|
{%- if not tools is defined %}
|
|
{%- set tools = [] %}
|
|
{%- endif %}
|
|
|
|
{%- if system_message is defined %}
|
|
{{- "<|im_start|>system\n" + system_message }}
|
|
{%- else %}
|
|
{%- if tools is iterable and tools | length > 0 %}
|
|
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
|
|
{%- endif %}
|
|
{%- endif %}
|
|
{%- if tools is iterable and tools | length > 0 %}
|
|
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
|
|
{{- "<tools>" }}
|
|
{%- for tool in tools %}
|
|
{%- if tool.function is defined %}
|
|
{%- set tool = tool.function %}
|
|
{%- endif %}
|
|
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
|
{%- if tool.description is defined %}
|
|
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
|
{%- endif %}
|
|
{{- '\n<parameters>' }}
|
|
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
|
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
|
{{- '\n<parameter>' }}
|
|
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
|
{%- if param_fields.type is defined %}
|
|
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
|
{%- endif %}
|
|
{%- if param_fields.description is defined %}
|
|
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
|
{%- endif %}
|
|
{%- set handled_keys = ['name', 'type', 'description'] %}
|
|
{{- render_extra_keys(param_fields, handled_keys) }}
|
|
{{- '\n</parameter>' }}
|
|
{%- endfor %}
|
|
{%- endif %}
|
|
{% set handled_keys = ['type', 'properties'] %}
|
|
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
|
{{- '\n</parameters>' }}
|
|
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
|
{{- render_extra_keys(tool, handled_keys) }}
|
|
{{- '\n</function>' }}
|
|
{%- endfor %}
|
|
{{- "\n</tools>" }}
|
|
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
|
{%- endif %}
|
|
{%- if system_message is defined %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- else %}
|
|
{%- if tools is iterable and tools | length > 0 %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- endif %}
|
|
{%- endif %}
|
|
{%- for message in loop_messages %}
|
|
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
|
{{- '<|im_start|>' + message.role }}
|
|
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
|
|
{{- '\n' + message.content | trim + '\n' }}
|
|
{%- endif %}
|
|
{%- for tool_call in message.tool_calls %}
|
|
{%- if tool_call.function is defined %}
|
|
{%- set tool_call = tool_call.function %}
|
|
{%- endif %}
|
|
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
|
{%- if tool_call.arguments is defined %}
|
|
{%- for args_name, args_value in tool_call.arguments|items %}
|
|
{{- '<parameter=' + args_name + '>\n' }}
|
|
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
|
{{- args_value }}
|
|
{{- '\n</parameter>\n' }}
|
|
{%- endfor %}
|
|
{%- endif %}
|
|
{{- '</function>\n</tool_call>' }}
|
|
{%- endfor %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
|
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
|
{%- elif message.role == "tool" %}
|
|
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
|
{{- '<|im_start|>user\n' }}
|
|
{%- endif %}
|
|
{{- '<tool_response>\n' }}
|
|
{{- message.content }}
|
|
{{- '\n</tool_response>\n' }}
|
|
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- elif loop.last %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- endif %}
|
|
{%- else %}
|
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
|
{%- endif %}
|
|
{%- endfor %}
|
|
{%- if add_generation_prompt %}
|
|
{{- '<|im_start|>assistant\n' }}
|
|
{%- endif %}
|