NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 / nano_v3_reasoning_parser.py
suhara's picture
Upload nano_v3_reasoning_parser.py
f6aca92 verified
raw
history blame contribute delete
798 Bytes
from vllm.reasoning.abs_reasoning_parsers import ReasoningParserManager
from vllm.reasoning.deepseek_r1_reasoning_parser import DeepSeekR1ReasoningParser
@ReasoningParserManager.register_module("nano_v3")
class NanoV3ReasoningParser(DeepSeekR1ReasoningParser):
def extract_reasoning(self, model_output, request):
reasoning_content, final_content = super().extract_reasoning(
model_output, request
)
if (
hasattr(request, "chat_template_kwargs")
and request.chat_template_kwargs
and request.chat_template_kwargs.get("enable_thinking") is False
and final_content is None
):
reasoning_content, final_content = final_content, reasoning_content
return reasoning_content, final_content