llama.cpp/examples/high_level_api/high_level_api_streaming.py
2023-04-05 04:10:13 -04:00

21 lines
447 B
Python

import json
import argparse
from llama_cpp import Llama
parser = argparse.ArgumentParser()
parser.add_argument("-m", "--model", type=str, default="./models/...")
args = parser.parse_args()
llm = Llama(model_path=args.model)
stream = llm(
"Question: What are the names of the planets in the solar system? Answer: ",
max_tokens=48,
stop=["Q:", "\n"],
stream=True,
)
for output in stream:
print(json.dumps(output, indent=2))