Harry MellorandClaude Opus 5
8c1557a79c
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Harry Mellor <hej.mellor@gmail.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
71 lines
2.0 KiB
Python
71 lines
2.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Example online usage of sequence reward models.
|
|
|
|
Run `vllm serve <model> --runner pooling`
|
|
to start up the server in vLLM. e.g.
|
|
|
|
vllm serve Skywork/Skywork-Reward-V2-Qwen3-0.6B
|
|
|
|
The key distinction between sequence classification and token classification
|
|
lies in their output granularity: sequence classification produces a single
|
|
result for an entire input sequence, whereas token classification yields a
|
|
result for each individual token within the sequence.
|
|
"""
|
|
|
|
import argparse
|
|
import pprint
|
|
|
|
import requests
|
|
|
|
|
|
def post_http_request(prompt: dict, api_url: str) -> requests.Response:
|
|
headers = {"User-Agent": "Test Client"}
|
|
response = requests.post(api_url, headers=headers, json=prompt)
|
|
return response
|
|
|
|
|
|
def parse_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--host", type=str, default="localhost")
|
|
parser.add_argument("--port", type=int, default=8000)
|
|
|
|
return parser.parse_args()
|
|
|
|
|
|
def main(args):
|
|
base_url = f"http://{args.host}:{args.port}"
|
|
models_url = base_url + "/v1/models"
|
|
pooing_url = base_url + "/pooling"
|
|
|
|
response = requests.get(models_url)
|
|
model = response.json()["data"][0]["id"]
|
|
|
|
# Input like Completions API
|
|
prompt = {"model": model, "input": "vLLM is great!"}
|
|
pooling_response = post_http_request(prompt=prompt, api_url=pooing_url)
|
|
print("-" * 50)
|
|
print("Pooling Response:")
|
|
pprint.pprint(pooling_response.json())
|
|
print("-" * 50)
|
|
|
|
# Input like Chat API
|
|
prompt = {
|
|
"model": model,
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": [{"type": "text", "text": "vLLM is great!"}],
|
|
}
|
|
],
|
|
}
|
|
pooling_response = post_http_request(prompt=prompt, api_url=pooing_url)
|
|
print("Pooling Response:")
|
|
pprint.pprint(pooling_response.json())
|
|
print("-" * 50)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
args = parse_args()
|
|
main(args)
|