Qwen3-30B-A3B-Thinking-2507

MERA Создан 03.03.2026 16:33

Оценки по задачам лидерборда

Таблица скроллится влево

Задача Результат Место в рейтинге
Сельское хозяйство 0.606 5
Медицина и здравоохранение 0.828 3

Информация о сабмите

Версия MERA
v1.0.0
Версия Torch
2.9.1
Версия кодовой базы
7c56310
Версия CUDA
12.8
Precision весов модели
bfloat16
Сид
1234
Батч
1
Версия transformers
4.56.1
Количество GPU и их тип
4 x NVIDIA A100-SXM4-80GB
Архитектура
local-chat-completions

Команда:

MERA

Название ML-модели:

Qwen3-30B-A3B-Thinking-2507

Ссылка на ML-модель:

https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507

Размер модели

30.0B

Тип модели:

Открытая

SFT

Дополнительные ссылки:

https://arxiv.org/abs/2505.09388

Описание архитектуры:

Qwen3-30B-A3B-Thinking-2507 is a decoder-only transformer language model from the Qwen3 family with approximately 30 billion parameters. The model is optimized for complex reasoning tasks and generates intermediate reasoning steps before producing the final answer. It supports long-context inputs and improved reasoning capabilities compared to earlier Qwen models.

Описание обучения:

The model follows the standard Qwen3 multi-stage training pipeline consisting of large-scale pretraining followed by post-training. Post-training includes instruction tuning and reinforcement-learning-based alignment to improve reasoning ability, instruction following, and response quality.

Данные претрейна:

The model was pretrained on a large multilingual corpus of approximately 36 trillion tokens covering 119 languages. It was further post-trained on instruction-following and reasoning-oriented datasets to improve instruction following and reasoning performance.

Лицензия:

Apache License 2.0

Параметры инференса

Параметры генерации:
agro_bench - do_sample=false;until=["<|im_end|>"];max_gen_toks=10000; \naqua_bench - do_sample=false;until=["<|im_end|>"];max_gen_toks=10000; \nmed_bench - do_sample=false;until=["<|im_end|>"];max_gen_toks=10000;

Описание темплейта:
{%- if tools %} \n {{- '<|im_start|>system \n' }} \n {%- if messages[0].role == 'system' %} \n {{- messages[0].content + ' \n \n' }} \n {%- endif %} \n {{- "# Tools \n \nYou may call one or more functions to assist with the user query. \n \nYou are provided with function signatures within <tools></tools> XML tags: \n<tools>" }} \n {%- for tool in tools %} \n {{- " \n" }} \n {{- tool | tojson }} \n {%- endfor %} \n {{- " \n</tools> \n \nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags: \n<tool_call> \n{"name": <function-name>, "arguments": <args-json-object>} \n</tool_call><|im_end|> \n" }} \n{%- else %} \n {%- if messages[0].role == 'system' %} \n {{- '<|im_start|>system \n' + messages[0].content + '<|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" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %} \n {%- set ns.multi_step_tool = false %} \n {%- set ns.last_query_index = index %} \n {%- endif %} \n{%- endfor %} \n{%- for message in messages %} \n {%- if message.content is string %} \n {%- set content = message.content %} \n {%- else %} \n {%- set content = '' %} \n {%- endif %} \n {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} \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 {%- else %} \n {%- if '</think>' in content %} \n {%- set reasoning_content = content.split('</think>')[0].rstrip(' \n').split('<think>')[-1].lstrip(' \n') %} \n {%- set content = content.split('</think>')[-1].lstrip(' \n') %} \n {%- endif %} \n {%- endif %} \n {%- if loop.index0 > ns.last_query_index %} \n {%- if loop.last or (not loop.last and reasoning_content) %} \n {{- '<|im_start|>' + message.role + ' \n<think> \n' + reasoning_content.strip(' \n') + ' \n</think> \n \n' + content.lstrip(' \n') }} \n {%- else %} \n {{- '<|im_start|>' + message.role + ' \n' + content }} \n {%- endif %} \n {%- else %} \n {{- '<|im_start|>' + message.role + ' \n' + content }} \n {%- endif %} \n {%- if message.tool_calls %} \n {%- for tool_call in message.tool_calls %} \n {%- if (loop.first and content) or (not loop.first) %} \n {{- ' \n' }} \n {%- endif %} \n {%- if tool_call.function %} \n {%- set tool_call = tool_call.function %} \n {%- endif %} \n {{- '<tool_call> \n{"name": "' }} \n {{- tool_call.name }} \n {{- '", "arguments": ' }} \n {%- if tool_call.arguments is string %} \n {{- tool_call.arguments }} \n {%- else %} \n {{- tool_call.arguments | tojson }} \n {%- endif %} \n {{- '} \n</tool_call>' }} \n {%- endfor %} \n {%- endif %} \n {{- '<|im_end|> \n' }} \n {%- elif message.role == "tool" %} \n {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} \n {{- '<|im_start|>user' }} \n {%- endif %} \n {{- ' \n<tool_response> \n' }} \n {{- content }} \n {{- ' \n</tool_response>' }} \n {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} \n {{- '<|im_end|> \n' }} \n {%- endif %} \n {%- endif %} \n{%- endfor %} \n{%- if add_generation_prompt %} \n {{- '<|im_start|>assistant \n<think> \n' }} \n{%- endif %}