release initial code

Co-authored-by: Ying Sheng <sqy1415@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: parasol-aser <3848358+parasol-aser@users.noreply.github.com>
Co-authored-by: LiviaSun <33578456+ChuyueSun@users.noreply.github.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
This commit is contained in:
Lianmin Zheng
2024-01-08 04:37:50 +00:00
parent f6d40df0ee
commit 22085081bb
145 changed files with 17802 additions and 2 deletions

View File

@@ -0,0 +1,26 @@
from sglang import function, system, user, assistant, gen, set_default_backend, Runtime
@function
def multi_turn_question(s, question_1, question_2):
s += system("You are a helpful assistant.")
s += user(question_1)
s += assistant(gen("answer_1", max_tokens=256))
s += user(question_2)
s += assistant(gen("answer_2", max_tokens=256))
runtime = Runtime("meta-llama/Llama-2-7b-chat-hf")
set_default_backend(runtime)
state = multi_turn_question.run(
question_1="What is the capital of the United States?",
question_2="List two local attractions.",
temperature=0,
stream=True,
)
for out in state.text_iter():
print(out, end="", flush=True)
print()
runtime.shutdown()