[Fix] Sync gemma4 chat template from hf (#39570)

Signed-off-by: Frederic Odermatt <frederic.odermatt@44ai.ch>
This commit is contained in:
FredericOdermatt
2026-05-02 05:06:54 +02:00
committed by GitHub
parent 5737770c6c
commit c408fdd663
+67 -44
View File
@@ -1,9 +1,9 @@
{%- macro format_parameters(properties, required) -%}
{%- macro format_parameters(properties, required, filter_keys=false) -%}
{%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
{%- set ns = namespace(found_first=false) -%}
{%- for key, value in properties | dictsort -%}
{%- set add_comma = false -%}
{%- if key not in standard_keys -%}
{%- if not filter_keys or key not in standard_keys -%}
{%- if ns.found_first %},{% endif -%}
{%- set ns.found_first = true -%}
{{ key }}:{
@@ -11,34 +11,15 @@
description:<|"|>{{ value['description'] }}<|"|>
{%- set add_comma = true -%}
{%- endif -%}
{%- if value['nullable'] %}
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
nullable:true
{%- endif -%}
{%- if value['type'] | upper == 'STRING' -%}
{%- if value['enum'] -%}
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
enum:{{ format_argument(value['enum']) }}
{%- endif -%}
{%- elif value['type'] | upper == 'OBJECT' -%}
,properties:{
{%- if value['properties'] is defined and value['properties'] is mapping -%}
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
{%- elif value is mapping -%}
{{- format_parameters(value, value['required'] | default([])) -}}
{%- endif -%}
}
{%- if value['required'] -%}
,required:[
{%- for item in value['required'] | default([]) -%}
<|"|>{{- item -}}<|"|>
{%- if not loop.last %},{% endif -%}
{%- endfor -%}
]
{%- endif -%}
{%- elif value['type'] | upper == 'ARRAY' -%}
{%- if value['items'] is mapping and value['items'] -%}
,items:{
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
items:{
{%- set ns_items = namespace(found_first=false) -%}
{%- for item_key, item_value in value['items'] | dictsort -%}
{%- if item_value is not none -%}
@@ -71,6 +52,32 @@
}
{%- endif -%}
{%- endif -%}
{%- if value['nullable'] %}
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
nullable:true
{%- endif -%}
{%- if value['type'] | upper == 'OBJECT' -%}
{%- if value['properties'] is defined and value['properties'] is mapping -%}
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
properties:{
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
}
{%- elif value is mapping -%}
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
properties:{
{{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
}
{%- endif -%}
{%- if value['required'] -%}
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
required:[
{%- for item in value['required'] | default([]) -%}
<|"|>{{- item -}}<|"|>
{%- if not loop.last %},{% endif -%}
{%- endfor -%}
]
{%- endif -%}
{%- endif -%}
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
type:<|"|>{{ value['type'] | upper }}<|"|>}
{%- endif -%}
@@ -167,20 +174,25 @@
{%- set ns = namespace(prev_message_type=None) -%}
{%- set loop_messages = messages -%}
{{ bos_token }}
{{- bos_token -}}
{#- Handle System/Tool Definitions Block -#}
{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
{{- '<|turn>system\n' -}}
{#- Inject Thinking token at the very top of the FIRST system turn -#}
{%- if enable_thinking is defined and enable_thinking -%}
{{- '<|think|>' -}}
{{- '<|think|>\n' -}}
{%- set ns.prev_message_type = 'think' -%}
{%- endif -%}
{%- if messages[0]['role'] in ['system', 'developer'] -%}
{{- messages[0]['content'] | trim -}}
{%- if messages[0]['content'] is string -%}
{{- messages[0]['content'] | trim -}}
{%- elif messages[0]['content'] is sequence -%}
{%- for item in messages[0]['content'] -%}
{{- item['text'] | trim + ' '-}}
{%- endfor -%}
{%- endif -%}
{%- set loop_messages = messages[1:] -%}
{%- endif -%}
{%- if tools -%}
{%- for tool in tools %}
{{- '<|tool>' -}}
@@ -189,10 +201,10 @@
{%- endfor %}
{%- set ns.prev_message_type = 'tool' -%}
{%- endif -%}
{{- '<turn|>\n' -}}
{%- endif %}
{#- Pre-scan: find last user message index for reasoning guard -#}
{%- set ns_turn = namespace(last_user_idx=-1) -%}
{%- for i in range(loop_messages | length) -%}
{%- if loop_messages[i]['role'] == 'user' -%}
@@ -200,12 +212,12 @@
{%- endif -%}
{%- endfor -%}
{#- Loop through messages -#}
{%- for message in loop_messages -%}
{%- if message['role'] != 'tool' -%}
{%- set ns.prev_message_type = None -%}
{%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
{#- OpenAI may emit multiple assistant messages in one tool loop (user → asst → tool → asst → tool).
Only the first of those should open <|turn>model; later ones continue the same model turn. -#}
{#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
{%- set prev_nt = namespace(role=None, found=false) -%}
{%- if loop.index0 > 0 -%}
{%- for j in range(loop.index0 - 1, -1, -1) -%}
@@ -222,8 +234,10 @@
{{- '<|turn>' + role + '\n' }}
{%- endif -%}
{%- if message.get('reasoning') and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
{{- '<|channel>thought\n' + message['reasoning'] + '\n<channel|>'}}
{#- Render reasoning/reasoning_content as thinking channel -#}
{%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
{%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
{{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
{%- endif -%}
{%- if message['tool_calls'] -%}
@@ -247,14 +261,14 @@
{%- set ns_tr_out = namespace(flag=false) -%}
{%- if message.get('tool_responses') -%}
{#- Legacy: tool_responses embedded on the assistant message -#}
{#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
{%- for tool_response in message['tool_responses'] -%}
{{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
{%- set ns_tr_out.flag = true -%}
{%- set ns.prev_message_type = 'tool_response' -%}
{%- endfor -%}
{%- elif message.get('tool_calls') -%}
{#- OpenAI Chat Completions: consecutive following messages with role "tool" (no break/continue; range scan) -#}
{#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
{%- set ns_tool_scan = namespace(stopped=false) -%}
{%- for k in range(loop.index0 + 1, loop_messages | length) -%}
{%- if ns_tool_scan.stopped -%}
@@ -262,12 +276,14 @@
{%- set ns_tool_scan.stopped = true -%}
{%- else -%}
{%- set follow = loop_messages[k] -%}
{#- Resolve tool_call_id to function name -#}
{%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
{%- for tc in message['tool_calls'] -%}
{%- if tc.get('id') == follow.get('tool_call_id') -%}
{%- set ns_tname.name = tc['function']['name'] -%}
{%- endif -%}
{%- endfor -%}
{#- Handle content as string or content-parts array -#}
{%- set tool_body = follow.get('content') -%}
{%- if tool_body is string -%}
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
@@ -288,6 +304,7 @@
{%- endfor -%}
{%- endif -%}
{%- set captured_content -%}
{%- if message['content'] is string -%}
{%- if role == 'model' -%}
{{- strip_thinking(message['content']) -}}
@@ -303,29 +320,35 @@
{{- item['text'] | trim -}}
{%- endif -%}
{%- elif item['type'] == 'image' -%}
{{- '\n\n<|image|>\n\n' -}}
{{- '<|image|>' -}}
{%- set ns.prev_message_type = 'image' -%}
{%- elif item['type'] == 'audio' -%}
{{- '<|audio|>' -}}
{%- set ns.prev_message_type = 'audio' -%}
{%- elif item['type'] == 'video' -%}
{{- '\n\n<|video|>\n\n' -}}
{{- '<|video|>' -}}
{%- set ns.prev_message_type = 'video' -%}
{%- endif -%}
{%- endfor -%}
{%- endif -%}
{%- endset -%}
{%- if not (ns_tr_out.flag and not message.get('content')) -%}
{{- captured_content -}}
{%- set has_content = captured_content | trim | length > 0 -%}
{%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
{{- '<|tool_response>' -}}
{%- elif not (ns_tr_out.flag and not has_content) -%}
{{- '<turn|>\n' -}}
{%- endif -%}
{%- endif -%}
{%- endfor -%}
{%- if add_generation_prompt -%}
{%- if ns.prev_message_type != 'tool_response' -%}
{%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
{{- '<|turn>model\n' -}}
{%- if not enable_thinking | default(false) -%}
{{- '<|channel>thought\n<channel|>' -}}
{%- endif -%}
{%- endif -%}
{%- if not enable_thinking | default(false) -%}
{{- '<|channel>thought\n<channel|>' -}}
{%- endif -%}
{%- endif -%}
{%- endif -%}