ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[data] qwen3 fixes (#8109)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-05-20 02:00:30 +08:00
committed by GitHub
parent 45030ff803
commit 9b5baa97f0
13 changed files with 197 additions and 160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llamafactory/chat/hf_engine.py
View File

@@ -104,10 +104,7 @@ class HuggingfaceEngine(BaseEngine):
messages, mm_input_dict["images"], mm_input_dict["videos"], mm_input_dict["audios"], processor
)
paired_messages = messages + [{"role": "assistant", "content": ""}]
system = system or generating_args["default_system"]
enable_thinking = input_kwargs.pop("enable_thinking", None)
enable_thinking = enable_thinking if enable_thinking is not None else generating_args["enable_thinking"]
prompt_ids, _ = template.encode_oneturn(tokenizer, paired_messages, system, tools, enable_thinking)
prompt_ids, _ = template.encode_oneturn(tokenizer, paired_messages, system, tools)
prompt_ids, _ = template.mm_plugin.process_token_ids(
prompt_ids,
None,

5
src/llamafactory/chat/sglang_engine.py
View File

@@ -160,10 +160,7 @@ class SGLangEngine(BaseEngine):
messages, images or [], videos or [], audios or [], self.processor
)
paired_messages = messages + [{"role": "assistant", "content": ""}]
system = system or self.generating_args["default_system"]
enable_thinking = input_kwargs.pop("enable_thinking", None)
enable_thinking = enable_thinking if enable_thinking is not None else self.generating_args["enable_thinking"]
prompt_ids, _ = self.template.encode_oneturn(self.tokenizer, paired_messages, system, tools, enable_thinking)
prompt_ids, _ = self.template.encode_oneturn(self.tokenizer, paired_messages, system, tools)
prompt_length = len(prompt_ids)
temperature: Optional[float] = input_kwargs.pop("temperature", None)

5
src/llamafactory/chat/vllm_engine.py
View File

@@ -124,10 +124,7 @@ class VllmEngine(BaseEngine):
messages, images or [], videos or [], audios or [], self.processor
)
paired_messages = messages + [{"role": "assistant", "content": ""}]
system = system or self.generating_args["default_system"]
enable_thinking = input_kwargs.pop("enable_thinking", None)
enable_thinking = enable_thinking if enable_thinking is not None else self.generating_args["enable_thinking"]
prompt_ids, _ = self.template.encode_oneturn(self.tokenizer, paired_messages, system, tools, enable_thinking)
prompt_ids, _ = self.template.encode_oneturn(self.tokenizer, paired_messages, system, tools)
prompt_length = len(prompt_ids)
temperature: Optional[float] = input_kwargs.pop("temperature", None)