feat: support training with JSON string tool arguments (#3136)

* feat: support training with JSON string tool arguments; fix PyArrow data type inconsistent error

* feat: raise error for tool call arguments decode

* Add test_chat_templates_tool_call_string_arguments.py

Add test for string arguments

* fix: change to correct qwen3 tokenizer

* fix: update docs to clarify arguments json

* chore: lint

* fix: duplicate

* chore: revert

* feat: add error to faq

* fix: remove duplicate fixture

---------

Co-authored-by: caoqinping <caoqinping@lixiang.com>
Co-authored-by: gamersover-blog <1611885128@qq.com>
Co-authored-by: NanoCode012 <nano@axolotl.ai>
This commit is contained in:
陈华杰
2025-09-25 13:06:21 +08:00
committed by GitHub
parent 856ff12171
commit e8b962d47f
7 changed files with 252 additions and 20 deletions

View File

@@ -177,6 +177,15 @@ def fixture_devstral_1_1_tokenizer():
return tokenizer
@pytest.fixture(name="qwen3_tokenizer")
def qwen3_tokenizer_fixture(
download_qwen3_half_billion_model,
): # pylint: disable=unused-argument,redefined-outer-name
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
return tokenizer
@pytest.fixture(name="mistralv03_tokenizer_chat_template_jinja")
def fixture_mistralv03_chat_template_jinja_w_system() -> str:
return '{%- if messages[0]["role"] == "system" %}\n {%- set system_message = messages[0]["content"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}\n\n{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}\n{%- set ns = namespace() %}\n{%- set ns.index = 0 %}\n{%- for message in loop_messages %}\n {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}\n {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}\n {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}\n {%- endif %}\n {%- set ns.index = ns.index + 1 %}\n {%- endif %}\n{%- endfor %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if message["role"] == "user" %}\n {%- if tools is not none and (message == user_messages[-1]) %}\n {{- "[AVAILABLE_TOOLS] [" }}\n {%- for tool in tools %}\n {%- set tool = tool.function %}\n {{- \'{"type": "function", "function": {\' }}\n {%- for key, val in tool.items() if key != "return" %}\n {%- if val is string %}\n {{- \'"\' + key + \'": "\' + val + \'"\' }}\n {%- else %}\n {{- \'"\' + key + \'": \' + val|tojson }}\n {%- endif %}\n {%- if not loop.last %}\n {{- ", " }}\n {%- endif %}\n {%- endfor %}\n {{- "}}" }}\n {%- if not loop.last %}\n {{- ", " }}\n {%- else %}\n {{- "]" }}\n {%- endif %}\n {%- endfor %}\n {{- "[/AVAILABLE_TOOLS]" }}\n {%- endif %}\n {%- if loop.first and system_message is defined %}\n {{- "[INST] " + system_message + "\\n\\n" + message["content"] + "[/INST]" }}\n {%- else %}\n {{- "[INST] " + message["content"] + "[/INST]" }}\n {%- endif %}\n {%- elif message.tool_calls is defined and message.tool_calls is not none %}\n {{- "[TOOL_CALLS] [" }}\n {%- for tool_call in message.tool_calls %}\n {%- set out = tool_call.function|tojson %}\n {{- out[:-1] }}\n {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}\n {%- endif %}\n {{- \', "id": "\' + tool_call.id + \'"}\' }}\n {%- if not loop.last %}\n {{- ", " }}\n {%- else %}\n {{- "]" + eos_token }}\n {%- endif %}\n {%- endfor %}\n {%- elif message["role"] == "assistant" %}\n {{- " " + message["content"]|trim + eos_token}}\n {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}\n {%- if message.content is defined and message.content.content is defined %}\n {%- set content = message.content.content %}\n {%- else %}\n {%- set content = message.content %}\n {%- endif %}\n {{- \'[TOOL_RESULTS] {"content": \' + content|string + ", " }}\n {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}\n {%- endif %}\n {{- \'"call_id": "\' + message.tool_call_id + \'"}[/TOOL_RESULTS]\' }}\n {%- else %}\n {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}\n {%- endif %}\n{%- endfor %}\n'