3b19e39dc5
Co-authored-by: nunjunj <ray@g-3ff9f30f2ed650001.c.vllm-405802.internal> Co-authored-by: nunjunj <ray@g-1df6075697c3f0001.c.vllm-405802.internal> Co-authored-by: nunjunj <ray@g-c5a2c23abc49e0001.c.vllm-405802.internal> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
54 lines
1.3 KiB
Python
54 lines
1.3 KiB
Python
from vllm import LLM, SamplingParams
|
|
|
|
llm = LLM(model="meta-llama/Meta-Llama-3-8B-Instruct")
|
|
sampling_params = SamplingParams(temperature=0.5)
|
|
|
|
|
|
def print_outputs(outputs):
|
|
for output in outputs:
|
|
prompt = output.prompt
|
|
generated_text = output.outputs[0].text
|
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|
|
print("-" * 80)
|
|
|
|
|
|
print("=" * 80)
|
|
|
|
# In this script, we demonstrate how to pass input to the chat method:
|
|
|
|
conversation = [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful assistant"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Hello"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Hello! How can I assist you today?"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Write an essay about the importance of higher education.",
|
|
},
|
|
]
|
|
outputs = llm.chat(conversation,
|
|
sampling_params=sampling_params,
|
|
use_tqdm=False)
|
|
print_outputs(outputs)
|
|
|
|
# A chat template can be optionally supplied.
|
|
# If not, the model will use its default chat template.
|
|
|
|
# with open('template_falcon_180b.jinja', "r") as f:
|
|
# chat_template = f.read()
|
|
|
|
# outputs = llm.chat(
|
|
# conversations,
|
|
# sampling_params=sampling_params,
|
|
# use_tqdm=False,
|
|
# chat_template=chat_template,
|
|
# )
|