Files changed (2) hide show
  1. README.md +3 -6
  2. tokenizer_config.json +2 -2
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: transformers
3
- license: apache-2.0
4
  license_link: https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8/blob/main/LICENSE
5
  pipeline_tag: text-generation
6
  base_model:
@@ -69,11 +69,8 @@ For more details, including benchmark evaluation, hardware requirements, and inf
69
  | WritingBench | 74.5 | 75.5 | 79.2 | **86.2** | 77.0 | 85.2 |
70
  | **Agent** | | | | | | |
71
  | BFCL-v3 | 64.7 | 66.5 | 60.1 | 65.2 | 68.0 | **70.9** |
72
- | TAU1-Retail | 49.6 | 60.3# | **81.4** | 70.7 | 65.2 | 71.3 |
73
- | TAU1-Airline | 32.0 | 42.8# | **59.6** | 53.5 | 32.0 | 44.0 |
74
- | TAU2-Retail | 71.1 | 66.7# | **75.5** | 70.6 | 64.9 | 74.6 |
75
- | TAU2-Airline | 36.0 | 42.0# | 55.5 | **56.5** | 36.0 | 50.0 |
76
- | TAU2-Telecom | 34.0 | 29.8# | 45.2 | **65.8** | 24.6 | 32.5 |
77
  | **Multilingualism** | | | | | | |
78
  | MultiIF | 66.5 | 70.4 | - | 76.2 | 70.2 | **77.5** |
79
  | MMLU-ProX | 75.8 | 76.2 | - | 74.5 | 73.2 | **79.4** |
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
  license_link: https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8/blob/main/LICENSE
5
  pipeline_tag: text-generation
6
  base_model:
 
69
  | WritingBench | 74.5 | 75.5 | 79.2 | **86.2** | 77.0 | 85.2 |
70
  | **Agent** | | | | | | |
71
  | BFCL-v3 | 64.7 | 66.5 | 60.1 | 65.2 | 68.0 | **70.9** |
72
+ | TAU-Retail | 49.6 | 60.3# | **81.4** | 70.7 | 65.2 | 71.3 |
73
+ | TAU-Airline | 32.0 | 42.8# | **59.6** | 53.5 | 32.0 | 44.0 |
 
 
 
74
  | **Multilingualism** | | | | | | |
75
  | MultiIF | 66.5 | 70.4 | - | 76.2 | 70.2 | **77.5** |
76
  | MMLU-ProX | 75.8 | 76.2 | - | 74.5 | 73.2 | **79.4** |
tokenizer_config.json CHANGED
@@ -226,11 +226,11 @@
226
  "<|video_pad|>"
227
  ],
228
  "bos_token": null,
229
- "chat_template": "{%- 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{%- 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 {{- '<|im_start|>' + message.role + '\\n' + content }}\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' }}\n{%- endif %}",
230
  "clean_up_tokenization_spaces": false,
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
- "model_max_length": 1010000,
234
  "pad_token": "<|endoftext|>",
235
  "split_special_tokens": false,
236
  "tokenizer_class": "Qwen2Tokenizer",
 
226
  "<|video_pad|>"
227
  ],
228
  "bos_token": null,
229
+ "chat_template": "{%- 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' }}\n{%- endif %}",
230
  "clean_up_tokenization_spaces": false,
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
+ "model_max_length": 262144,
234
  "pad_token": "<|endoftext|>",
235
  "split_special_tokens": false,
236
  "tokenizer_class": "Qwen2Tokenizer",