File size: 1,554 Bytes
cb2428f |
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 |
# Copyright (c) Alibaba, Inc. and its affiliates.
import os
from openai import OpenAI
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
def infer(client, model: str, messages):
resp = client.chat.completions.create(model=model, messages=messages, max_tokens=512, temperature=0)
query = messages[0]['content']
response = resp.choices[0].message.content
print(f'query: {query}')
print(f'response: {response}')
return response
# streaming
def infer_stream(client, model: str, messages):
gen = client.chat.completions.create(model=model, messages=messages, stream=True, temperature=0)
print(f'messages: {messages}\nresponse: ', end='')
for chunk in gen:
print(chunk.choices[0].delta.content, end='', flush=True)
print()
def run_client(host: str = '127.0.0.1', port: int = 8000):
client = OpenAI(
api_key='EMPTY',
base_url=f'http://{host}:{port}/v1',
)
model = client.models.list().data[0].id
print(f'model: {model}')
query = 'Where is the capital of Zhejiang?'
messages = [{'role': 'user', 'content': query}]
response = infer(client, model, messages)
messages.append({'role': 'assistant', 'content': response})
messages.append({'role': 'user', 'content': 'What delicious food is there?'})
infer_stream(client, model, messages)
if __name__ == '__main__':
from swift.llm import run_deploy, DeployArguments
with run_deploy(DeployArguments(model='Qwen/Qwen2.5-1.5B-Instruct', verbose=False, log_interval=-1)) as port:
run_client(port=port)
|