■ HuggingFacePipeline 클래스의 from_model_id 정적 메소드에서 batch_size 인자를 사용해 배치 처리 크기를 설정하는 방법을 보여준다.
▶ main.py
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
from langchain_huggingface import HuggingFacePipeline from langchain.prompts import PromptTemplate huggingFacePipeline = HuggingFacePipeline.from_model_id( model_id = "beomi/llama-2-ko-7b", task = "text-generation", device = 0, batch_size = 2, model_kwargs = { "temperature" : 0, "max_length" : 256 } ) promptTemplateString = """Answer the following question in Korean. #Question : {question} #Answer : """ promptTemplate = PromptTemplate.from_template(promptTemplateString) runnableSequence = promptTemplate | huggingFacePipeline.bind(stop = ["\n\n"]) questionList = [] for i in range(4): questionList.append({"question" : f"숫자 {i} 이 한글로 무엇입니까?"}) responseList = runnableSequence.batch(questionList) for response in responseList: print(response) |
▶ requirements.txt
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
aiohappyeyeballs==2.4.4 aiohttp==3.11.11 aiosignal==1.3.2 annotated-types==0.7.0 anyio==4.8.0 async-timeout==4.0.3 attrs==24.3.0 certifi==2024.12.14 charset-normalizer==3.4.1 exceptiongroup==1.2.2 filelock==3.16.1 frozenlist==1.5.0 fsspec==2024.12.0 greenlet==3.1.1 h11==0.14.0 httpcore==1.0.7 httpx==0.28.1 huggingface-hub==0.27.1 idna==3.10 Jinja2==3.1.5 joblib==1.4.2 jsonpatch==1.33 jsonpointer==3.0.0 langchain==0.3.14 langchain-core==0.3.29 langchain-huggingface==0.1.2 langchain-text-splitters==0.3.5 langsmith==0.2.10 MarkupSafe==3.0.2 mpmath==1.3.0 multidict==6.1.0 networkx==3.4.2 numpy==1.26.4 nvidia-cublas-cu12==12.4.5.8 nvidia-cuda-cupti-cu12==12.4.127 nvidia-cuda-nvrtc-cu12==12.4.127 nvidia-cuda-runtime-cu12==12.4.127 nvidia-cudnn-cu12==9.1.0.70 nvidia-cufft-cu12==11.2.1.3 nvidia-curand-cu12==10.3.5.147 nvidia-cusolver-cu12==11.6.1.9 nvidia-cusparse-cu12==12.3.1.170 nvidia-nccl-cu12==2.21.5 nvidia-nvjitlink-cu12==12.4.127 nvidia-nvtx-cu12==12.4.127 orjson==3.10.14 packaging==24.2 pillow==11.1.0 propcache==0.2.1 pydantic==2.10.5 pydantic_core==2.27.2 PyYAML==6.0.2 regex==2024.11.6 requests==2.32.3 requests-toolbelt==1.0.0 safetensors==0.5.2 scikit-learn==1.6.1 scipy==1.15.1 sentence-transformers==3.3.1 sniffio==1.3.1 SQLAlchemy==2.0.37 sympy==1.13.1 tenacity==9.0.0 threadpoolctl==3.5.0 tokenizers==0.21.0 torch==2.5.1 tqdm==4.67.1 transformers==4.48.0 triton==3.1.0 typing_extensions==4.12.2 urllib3==2.3.0 yarl==1.18.3 |
※ pip install langchain langchain-huggingface 명령을 실행했다.