import os
os.environ["CUDA_VISIBLE_DEVICES"]="6,7"
from vllm import LLM, SamplingParams
llm = LLM('/data-ai/model/llama2/llama2_hf/Llama-2-13b-chat-hf')
prompts =["Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
outputs = llm.generate(prompts, sampling_params)# Print the outputs.foroutputin outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
Prompt: 'Hello, my name is', Generated text: " Sherry and I'm a stay at home mom of three beautiful children."
Prompt: 'The president of the United States is', Generated text: ' one of the most powerful people in the world, and yet, many people do'
Prompt: 'The capital of France is', Generated text: ' Paris. This is a fact that is well known to most people, but there'
Prompt: 'The future of AI is', Generated text: ' likely to be shaped by a combination of technological advancements and soci'