Update chat template, tokenizer and generation config
Browse files- chat_template.jinja +24 -13
- generation_config.json +1 -1
- tokenizer_config.json +3 -3
chat_template.jinja
CHANGED
|
@@ -27,11 +27,6 @@
|
|
| 27 |
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
{%- endif %}
|
| 29 |
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'audio' in item or item.type == 'audio' %}
|
| 31 |
-
{%- if is_system_content %}
|
| 32 |
-
{{- raise_exception('System message cannot contain audio.') }}
|
| 33 |
-
{%- endif %}
|
| 34 |
-
{{- '<|audio_start|><|audio_pad|><|audio_end|>' }}
|
| 35 |
{%- elif 'text' in item %}
|
| 36 |
{{- item.text }}
|
| 37 |
{%- else %}
|
|
@@ -47,8 +42,23 @@
|
|
| 47 |
{%- if not messages %}
|
| 48 |
{{- raise_exception('No messages provided.') }}
|
| 49 |
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
{%- if tools and tools is iterable and tools is not mapping %}
|
| 51 |
{{- '<|im_start|>system\n' }}
|
|
|
|
|
|
|
|
|
|
| 52 |
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 53 |
{%- for tool in tools %}
|
| 54 |
{{- "\n" }}
|
|
@@ -66,7 +76,13 @@
|
|
| 66 |
{%- else %}
|
| 67 |
{%- if messages[0].role == 'system' %}
|
| 68 |
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 69 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
{%- endif %}
|
| 71 |
{%- endif %}
|
| 72 |
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
|
@@ -95,14 +111,9 @@
|
|
| 95 |
{%- set reasoning_content = '' %}
|
| 96 |
{%- if message.reasoning_content is string %}
|
| 97 |
{%- set reasoning_content = message.reasoning_content %}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{%- if '</think>' in content %}
|
| 100 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 101 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 102 |
-
{%- endif %}
|
| 103 |
{%- endif %}
|
| 104 |
{%- set reasoning_content = reasoning_content|trim %}
|
| 105 |
-
{%- if
|
| 106 |
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 107 |
{%- else %}
|
| 108 |
{{- '<|im_start|>' + message.role + '\n' + content }}
|
|
@@ -121,7 +132,7 @@
|
|
| 121 |
{%- else %}
|
| 122 |
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 123 |
{%- endif %}
|
| 124 |
-
{%- if tool_call.arguments is defined %}
|
| 125 |
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 126 |
{{- '<parameter=' + args_name + '>\n' }}
|
| 127 |
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
|
|
|
| 27 |
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
{%- endif %}
|
| 29 |
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
{%- elif 'text' in item %}
|
| 31 |
{{- item.text }}
|
| 32 |
{%- else %}
|
|
|
|
| 42 |
{%- if not messages %}
|
| 43 |
{{- raise_exception('No messages provided.') }}
|
| 44 |
{%- endif %}
|
| 45 |
+
{%- set reasoning_instructions = '' %}
|
| 46 |
+
{%- if enable_thinking is undefined or enable_thinking is true %}
|
| 47 |
+
{%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
|
| 48 |
+
{%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
|
| 49 |
+
{{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if resolved_reasoning_effort == 'xhigh' %}
|
| 52 |
+
{%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
|
| 53 |
+
{%- elif resolved_reasoning_effort == 'low' %}
|
| 54 |
+
{%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endif %}
|
| 57 |
{%- if tools and tools is iterable and tools is not mapping %}
|
| 58 |
{{- '<|im_start|>system\n' }}
|
| 59 |
+
{%- if reasoning_instructions %}
|
| 60 |
+
{{- reasoning_instructions + '\n\n' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 63 |
{%- for tool in tools %}
|
| 64 |
{{- "\n" }}
|
|
|
|
| 76 |
{%- else %}
|
| 77 |
{%- if messages[0].role == 'system' %}
|
| 78 |
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 79 |
+
{%- if content %}
|
| 80 |
+
{{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
|
| 81 |
+
{%- elif reasoning_instructions %}
|
| 82 |
+
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{%- elif reasoning_instructions %}
|
| 85 |
+
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
|
| 86 |
{%- endif %}
|
| 87 |
{%- endif %}
|
| 88 |
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
|
|
|
| 111 |
{%- set reasoning_content = '' %}
|
| 112 |
{%- if message.reasoning_content is string %}
|
| 113 |
{%- set reasoning_content = message.reasoning_content %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
{%- endif %}
|
| 115 |
{%- set reasoning_content = reasoning_content|trim %}
|
| 116 |
+
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
|
| 117 |
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 118 |
{%- else %}
|
| 119 |
{{- '<|im_start|>' + message.role + '\n' + content }}
|
|
|
|
| 132 |
{%- else %}
|
| 133 |
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 134 |
{%- endif %}
|
| 135 |
+
{%- if tool_call.arguments is defined and tool_call.arguments != '' %}
|
| 136 |
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 137 |
{{- '<parameter=' + args_name + '>\n' }}
|
| 138 |
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
generation_config.json
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
248044
|
| 7 |
],
|
| 8 |
"pad_token_id": 248044,
|
| 9 |
-
"temperature":
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.95
|
| 12 |
}
|
|
|
|
| 6 |
248044
|
| 7 |
],
|
| 8 |
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.95
|
| 12 |
}
|
tokenizer_config.json
CHANGED
|
@@ -282,11 +282,11 @@
|
|
| 282 |
"<|video_pad|>"
|
| 283 |
],
|
| 284 |
"bos_token": null,
|
| 285 |
-
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif '
|
| 286 |
"clean_up_tokenization_spaces": false,
|
| 287 |
"eos_token": "<|im_end|>",
|
| 288 |
"errors": "replace",
|
| 289 |
-
"model_max_length":
|
| 290 |
"pad_token": "<|endoftext|>",
|
| 291 |
"split_special_tokens": false,
|
| 292 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
@@ -302,4 +302,4 @@
|
|
| 302 |
"vision_bos_token": "<|vision_start|>",
|
| 303 |
"vision_eos_token": "<|vision_end|>"
|
| 304 |
}
|
| 305 |
-
}
|
|
|
|
| 282 |
"<|video_pad|>"
|
| 283 |
],
|
| 284 |
"bos_token": null,
|
| 285 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set reasoning_instructions = '' %}\n{%- if enable_thinking is undefined or enable_thinking is true %}\n {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}\n {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}\n {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}\n {%- endif %}\n {%- if resolved_reasoning_effort == 'xhigh' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}\n {%- elif resolved_reasoning_effort == 'low' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {%- if reasoning_instructions %}\n {{- reasoning_instructions + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\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>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '<|im_start|>system\\n' + (reasoning_instructions + '\\n\\n' if reasoning_instructions else '') + content + '<|im_end|>\\n' }}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined and tool_call.arguments != '' %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 286 |
"clean_up_tokenization_spaces": false,
|
| 287 |
"eos_token": "<|im_end|>",
|
| 288 |
"errors": "replace",
|
| 289 |
+
"model_max_length": 262144,
|
| 290 |
"pad_token": "<|endoftext|>",
|
| 291 |
"split_special_tokens": false,
|
| 292 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
| 302 |
"vision_bos_token": "<|vision_start|>",
|
| 303 |
"vision_eos_token": "<|vision_end|>"
|
| 304 |
}
|
| 305 |
+
}
|