ebce310b74
Co-authored-by: Dash Desai <1723932+iamontheinet@users.noreply.github.com> Co-authored-by: Aurick Qiao <qiao@aurick.net> Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com> Co-authored-by: Aurick Qiao <aurickq@users.noreply.github.com> Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
27 lines
856 B
Python
27 lines
856 B
Python
from vllm import LLM, SamplingParams
|
|
|
|
# Sample prompts.
|
|
prompts = [
|
|
"Hello, my name is",
|
|
"The president of the United States is",
|
|
"The capital of France is",
|
|
"The future of AI is",
|
|
]
|
|
# Create a sampling params object.
|
|
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
|
|
|
|
# Create an LLM.
|
|
llm = LLM(model="snowflake/snowflake-arctic-instruct",
|
|
quantization="deepspeedfp",
|
|
tensor_parallel_size=8,
|
|
trust_remote_code=True)
|
|
# Generate texts from the prompts. The output is a list of RequestOutput objects
|
|
# that contain the prompt, generated text, and other information.
|
|
|
|
outputs = llm.generate(prompts, sampling_params)
|
|
# Print the outputs.
|
|
for output in outputs:
|
|
prompt = output.prompt
|
|
generated_text = output.outputs[0].text
|
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|