Fix chat template including thinking token
Browse filesThe original chat template mask `{% generation %}` tag wrongly. I supposed that the original version was copied from other Qwen3 models that requires reasoning. This model, however, doesn't contain thinking tag, making finetuning with this tokenizer under `--assistant_only_loss` resulted in wrong assistant masking. This change fix the incorporation of think token for instruction model while also allowing proper masking for instruction tuning.
- chat_template.jinja +2 -26
chat_template.jinja
CHANGED
|
@@ -14,14 +14,6 @@
|
|
| 14 |
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
{%- endif %}
|
| 16 |
{%- endif %}
|
| 17 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
-
{%- for message in messages[::-1] %}
|
| 19 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
-
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
-
{%- set ns.multi_step_tool = false %}
|
| 22 |
-
{%- set ns.last_query_index = index %}
|
| 23 |
-
{%- endif %}
|
| 24 |
-
{%- endfor %}
|
| 25 |
{%- for message in messages %}
|
| 26 |
{%- if message.content is string %}
|
| 27 |
{%- set content = message.content %}
|
|
@@ -31,24 +23,7 @@
|
|
| 31 |
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
{%- elif message.role == "assistant" %}
|
| 34 |
-
{
|
| 35 |
-
{%- if message.reasoning_content is string %}
|
| 36 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
-
{%- else %}
|
| 38 |
-
{%- if '</think>' in content %}
|
| 39 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
-
{%- endif %}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
-
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
-
{%- else %}
|
| 47 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
-
{%- endif %}
|
| 49 |
-
{%- else %}
|
| 50 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
-
{%- endif %}
|
| 52 |
{%- if message.tool_calls %}
|
| 53 |
{%- for tool_call in message.tool_calls %}
|
| 54 |
{%- if (loop.first and content) or (not loop.first) %}
|
|
@@ -69,6 +44,7 @@
|
|
| 69 |
{%- endfor %}
|
| 70 |
{%- endif %}
|
| 71 |
{{- '<|im_end|>\n' }}
|
|
|
|
| 72 |
{%- elif message.role == "tool" %}
|
| 73 |
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
{{- '<|im_start|>user' }}
|
|
|
|
| 14 |
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
{%- endif %}
|
| 16 |
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
{%- for message in messages %}
|
| 18 |
{%- if message.content is string %}
|
| 19 |
{%- set content = message.content %}
|
|
|
|
| 23 |
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n'}}{% generation %}{{- content }}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
{%- if message.tool_calls %}
|
| 28 |
{%- for tool_call in message.tool_calls %}
|
| 29 |
{%- if (loop.first and content) or (not loop.first) %}
|
|
|
|
| 44 |
{%- endfor %}
|
| 45 |
{%- endif %}
|
| 46 |
{{- '<|im_end|>\n' }}
|
| 47 |
+
{% endgeneration %}
|
| 48 |
{%- elif message.role == "tool" %}
|
| 49 |
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 50 |
{{- '<|im_start|>user' }}
|