lananhyeuem

qwen3-32b-multilingual-rag-lora-n5

README

License: apache-2.0

Inference (vLLM)

python

from vllm import LLM, SamplingParamsfrom vllm.lora.request import LoRARequest llm = LLM(model="Qwen/Qwen3-32B", enable_lora=True, max_lora_rank=128,          trust_remote_code=True, dtype="bfloat16")sp = SamplingParams(temperature=0.0, max_tokens=512)out = llm.generate(prompts, sp,                   lora_request=LoRARequest("a", 1, "<local path to this adapter>"))