mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-10 06:25:01 +08:00
71b1c8b667
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com> Signed-off-by: Yeshwanth N <yeshsurya@gmail.com> Signed-off-by: yeshsurya <yeshsurya@gmail.com>
48 lines
1.2 KiB
Python
48 lines
1.2 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from argparse import Namespace
|
|
|
|
from vllm import LLM, EngineArgs
|
|
from vllm.utils.argparse_utils import FlexibleArgumentParser
|
|
|
|
|
|
def parse_args():
|
|
parser = FlexibleArgumentParser()
|
|
parser = EngineArgs.add_cli_args(parser)
|
|
# Set example specific arguments
|
|
parser.set_defaults(
|
|
model="BAAI/bge-reranker-v2-m3",
|
|
runner="pooling",
|
|
enforce_eager=True,
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
def main(args: Namespace):
|
|
# Sample prompts.
|
|
text_1 = "What is the capital of France?"
|
|
texts_2 = [
|
|
"The capital of Brazil is Brasilia.",
|
|
"The capital of France is Paris.",
|
|
]
|
|
|
|
# Create an LLM.
|
|
# You should pass runner="pooling" for cross-encoder models
|
|
llm = LLM(**vars(args))
|
|
|
|
# Generate scores. The output is a list of ScoringRequestOutputs.
|
|
outputs = llm.score(text_1, texts_2)
|
|
|
|
# Print the outputs.
|
|
print("\nGenerated Outputs:\n" + "-" * 60)
|
|
for text_2, output in zip(texts_2, outputs):
|
|
score = output.outputs.score
|
|
print(f"Pair: {[text_1, text_2]!r} \nScore: {score}")
|
|
print("-" * 60)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
args = parse_args()
|
|
main(args)
|