C Transformers 라이브러리는 GGML 모델을 위한 Python 바인딩을 제공합니다. 이 예제는 LangChain을 사용하여 C Transformers 모델과 상호작용하는 방법을 다룹니다. 설치 
pip install -qU  ctransformers
모델 로드 
from langchain_community.llms import CTransformers

llm = CTransformers(model="marella/gpt-2-ggml")
텍스트 생성 
print(llm.invoke("AI is going to"))
스트리밍 
from langchain_core.callbacks import StreamingStdOutCallbackHandler

llm = CTransformers(
    model="marella/gpt-2-ggml", callbacks=[StreamingStdOutCallbackHandler()]
)

response = llm.invoke("AI is going to")
LLMChain 
from langchain.chains import LLMChain
from langchain_core.prompts import PromptTemplate

template = """Question: {question}

Answer:"""

prompt = PromptTemplate.from_template(template)

llm_chain = LLMChain(prompt=prompt, llm=llm)

response = llm_chain.run("What is AI?")
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I