* Add files via upload * fix unit test * fix crashes for --reasoning-format=none * Patch buggy official MiniMax-M2 chat template * add upstream minja fix: https://github.com/ochafik/minja/pull/7 * Fix <think> token not generated * add test copied from https://github.com/ggml-org/llama.cpp/pull/16946 * cleanup * Hopes to fix the compilation error on CI * Delete chat template patching since it’s fixed by upstream Minja * Remove undeeded Minimax-M2 template patch https://github.com/ochafik/minja/pull/7#issuecomment-3480356100 * Add proper handling of optional parameters with test merged tests from: https://github.com/ggml-org/llama.cpp/pull/16946/commits/23d4bb75c485c12ac89f81c424dc03c87a640e8c * Fix making all tool parameters optional * Move xml tool parser to separate file * cleanup & add tests for GLM4.5 * add streaming tests & enhancement & cleanups Add streaming test for both GLM 4.5 and minimax-m2. Cleanup for preserved_tokens. Cleanup for grammar rule name. Enhance the parser's stability. * cleanup & add support for Kimi-K2 Qwen3-Coder Apriel-1.5 Xiaomi-MiMo * apply suggestions from reviewers * fix a misuse for data.grammar_lazy * fix grammar when tool have no argument * Fix `no triggers set for lazy grammar!` for GLM4.5/4.6. Insert additional stops for Kimi-K2 * update chat.cpp * fix grammar for GLM 4.5/4.6 * Try fix Jinja template for GLM * Try fix GLM-4.6.jinja * Update common/chat-parser-xml-toolcall.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update tests/test-chat.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * improve chat template for GLM, rename Kimi-K2 template to Kimi-K2-Thinking * Improve Kimi-K2 chat template * Fix unit test * 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: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
112 lines
4.2 KiB
Django/Jinja
112 lines
4.2 KiB
Django/Jinja
{%- macro render_content(msg) -%}
|
|
{%- set c = msg.get('content') -%}
|
|
{%- if c is string -%}
|
|
{{ c }}
|
|
{%- elif c is not none -%}
|
|
{% for content in c -%}
|
|
{% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
|
|
<|media_start|>image<|media_content|><|media_pad|><|media_end|>
|
|
{% else -%}
|
|
{{ content['text'] }}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{%- endif -%}
|
|
{%- endmacro -%}
|
|
|
|
{% macro set_roles(message) -%}
|
|
{%- set role_name = message.get('name') or message['role'] -%}
|
|
{%- if message['role'] == 'user' -%}
|
|
<|im_user|>{{role_name}}<|im_middle|>
|
|
{%- elif message['role'] == 'assistant' -%}
|
|
<|im_assistant|>{{role_name}}<|im_middle|>
|
|
{%- else -%}
|
|
<|im_system|>{{role_name}}<|im_middle|>
|
|
{%- endif -%}
|
|
{%- endmacro -%}
|
|
|
|
{%- set tool_response_queue = namespace(ids=[]) -%}
|
|
{%- set tool_call_counter = namespace(value=1) -%}
|
|
|
|
{%- macro render_toolcalls(message) -%}
|
|
<|tool_calls_section_begin|>
|
|
{%- for tool_call in message['tool_calls'] -%}
|
|
{%- if tool_call['id'] is defined -%}
|
|
{%- set formatted_id = tool_call['id'] -%}
|
|
{%- else -%}
|
|
{%- set formatted_id = 'functions.' + tool_call['function']['name'] + ':' + (tool_call_counter.value | string) -%}
|
|
{%- set tool_call_counter.value = tool_call_counter.value + 1 -%}
|
|
{%- endif -%}
|
|
{%- set _ = tool_response_queue.ids.append(formatted_id) -%}
|
|
<|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
|
|
{%- endfor -%}
|
|
<|tool_calls_section_end|>
|
|
{%- endmacro -%}
|
|
|
|
|
|
{# Find last non-tool-call assisitant message #}
|
|
{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
|
|
{%- for idx in range(messages|length-1, -1, -1) -%}
|
|
{%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
|
|
{%- set ns.last_non_tool_call_assistant_msg = idx -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
|
|
{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
|
|
{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
|
|
{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
|
|
|
|
{%- if tools -%}
|
|
<|im_system|>tool_declare<|im_middle|>{{ tools | tojson }}<|im_end|>
|
|
{%- endif -%}
|
|
|
|
{%- if messages|length == 0 or messages[0]['role'] != 'system' -%}
|
|
<|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
|
|
{%- endif -%}
|
|
|
|
{%- for message in hist_msgs -%}
|
|
{{set_roles(message)}}
|
|
{%- if message['role'] == 'assistant' -%}
|
|
<think></think>{{render_content(message)}}
|
|
{%- if message.get('tool_calls') -%}
|
|
{{render_toolcalls(message)}}
|
|
{%- endif -%}
|
|
{%- elif message['role'] == 'tool' -%}
|
|
{%- if tool_response_queue.ids -%}
|
|
{%- set tool_call_id = tool_response_queue.ids.pop(0) -%}
|
|
{%- else -%}
|
|
{%- set tool_call_id = 'functions.' + message.get('name', 'unknown') + ':' + (tool_call_counter.value | string) -%}
|
|
{%- endif -%}
|
|
## Return of {{ tool_call_id }}
|
|
{{render_content(message)}}
|
|
{%- elif message['content'] is not none -%}
|
|
{{render_content(message)}}
|
|
{%- endif -%}
|
|
<|im_end|>
|
|
{%- endfor -%}
|
|
|
|
{%- for message in suffix_msgs -%}
|
|
{{set_roles(message)}}
|
|
{%- if message['role'] == 'assistant' -%}
|
|
{%- set rc = message.get('reasoning_content', '') -%}
|
|
<think>{{rc}}</think>{{render_content(message)}}
|
|
{%- if message.get('tool_calls') -%}
|
|
{{render_toolcalls(message)}}
|
|
{%- endif -%}
|
|
{%- elif message['role'] == 'tool' -%}
|
|
{%- if tool_response_queue.ids -%}
|
|
{%- set tool_call_id = tool_response_queue.ids.pop(0) -%}
|
|
{%- else -%}
|
|
{%- set tool_call_id = 'functions.' + message.get('name', 'unknown') + ':' + (tool_call_counter.value | string) -%}
|
|
{%- endif -%}
|
|
## Return of {{ tool_call_id }}
|
|
{{render_content(message)}}
|
|
{%- elif message['content'] is not none -%}
|
|
{{render_content(message)}}
|
|
{%- endif -%}
|
|
<|im_end|>
|
|
{%- endfor -%}
|
|
|
|
|
|
{%- if add_generation_prompt -%}
|
|
<|im_assistant|>assistant<|im_middle|>
|
|
{%- endif -%}
|