Format Benchmark Code (#399)
This commit is contained in:
@@ -1,22 +1,25 @@
|
||||
import argparse
|
||||
import ast
|
||||
from collections import Counter
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
from collections import Counter
|
||||
|
||||
import numpy as np
|
||||
from sglang.test.test_utils import add_common_sglang_args_and_parse, select_sglang_backend
|
||||
from sglang.utils import read_jsonl, dump_state_text
|
||||
import sglang as sgl
|
||||
|
||||
import sglang as sgl
|
||||
from sglang.test.test_utils import (
|
||||
add_common_sglang_args_and_parse,
|
||||
select_sglang_backend,
|
||||
)
|
||||
from sglang.utils import dump_state_text, read_jsonl
|
||||
|
||||
INVALID = -9999999
|
||||
|
||||
|
||||
def get_answer_value(answer_str):
|
||||
answer_str = answer_str.replace(",", "")
|
||||
numbers = re.findall(r'\d+', answer_str)
|
||||
numbers = re.findall(r"\d+", answer_str)
|
||||
if len(numbers) < 1:
|
||||
return INVALID
|
||||
try:
|
||||
@@ -40,7 +43,9 @@ temp = 0.001
|
||||
|
||||
def propose_plan(s, question, num_branches):
|
||||
s += sgl.user(
|
||||
"""Please generate a high-level plan for solving the following question. As the first step, just say what method and idea you will use to solve the question. You can reorganize the information in the question. Do not do the actual calculation. Keep your response concise and within 80 words. Question: """ + question)
|
||||
"""Please generate a high-level plan for solving the following question. As the first step, just say what method and idea you will use to solve the question. You can reorganize the information in the question. Do not do the actual calculation. Keep your response concise and within 80 words. Question: """
|
||||
+ question
|
||||
)
|
||||
forks = s.fork(num_branches)
|
||||
forks += sgl.assistant(sgl.gen("plan", max_tokens=256, temperature=temp))
|
||||
return forks
|
||||
@@ -48,7 +53,8 @@ def propose_plan(s, question, num_branches):
|
||||
|
||||
def execute_plan(s, num_branches):
|
||||
s += sgl.user(
|
||||
"""The plan looks good! Now, use real numbers and do the calculation. Please solve the question step-by-step according to the high-level plan. Give me the final answer. Make your response short.""")
|
||||
"""The plan looks good! Now, use real numbers and do the calculation. Please solve the question step-by-step according to the high-level plan. Give me the final answer. Make your response short."""
|
||||
)
|
||||
forks = s.fork(num_branches)
|
||||
forks += sgl.assistant(sgl.gen("answer", max_tokens=256, temperature=temp))
|
||||
return forks
|
||||
@@ -56,7 +62,8 @@ def execute_plan(s, num_branches):
|
||||
|
||||
def reflect_solution(s, num_branches):
|
||||
s += sgl.user(
|
||||
"""Okay. Now, evaluate your own solution and give it a score on a scale of 1 to 5. Please do rigorous check of the correctness.""")
|
||||
"""Okay. Now, evaluate your own solution and give it a score on a scale of 1 to 5. Please do rigorous check of the correctness."""
|
||||
)
|
||||
forks = s.fork(num_branches)
|
||||
forks += sgl.assistant(sgl.gen("score", max_tokens=256, temperature=temp))
|
||||
return forks
|
||||
@@ -64,13 +71,13 @@ def reflect_solution(s, num_branches):
|
||||
|
||||
def get_final_answer(s, num_branches):
|
||||
s += sgl.user(
|
||||
"""Based on your reflection, do you change your mind? Now, give me the final answer after careful consideration.""")
|
||||
"""Based on your reflection, do you change your mind? Now, give me the final answer after careful consideration."""
|
||||
)
|
||||
forks = s.fork(num_branches)
|
||||
forks += sgl.assistant(sgl.gen("final_answer", max_tokens=256, temperature=temp))
|
||||
return forks
|
||||
|
||||
|
||||
|
||||
@sgl.function
|
||||
def tree_search(s, question, num_branches):
|
||||
plan_forks = propose_plan(s, question, num_branches)
|
||||
@@ -93,6 +100,7 @@ def tree_search(s, question, num_branches):
|
||||
|
||||
return solutions
|
||||
|
||||
|
||||
def main(args):
|
||||
lines = read_jsonl(args.data_path)
|
||||
|
||||
@@ -100,7 +108,7 @@ def main(args):
|
||||
num_branches = 2
|
||||
questions = []
|
||||
labels = []
|
||||
for i in range(len(lines[:args.num_questions])):
|
||||
for i in range(len(lines[: args.num_questions])):
|
||||
questions.append(lines[i]["question"])
|
||||
labels.append(get_answer_value(lines[i]["answer"]))
|
||||
assert all(l != INVALID for l in labels)
|
||||
@@ -112,7 +120,12 @@ def main(args):
|
||||
# Run requests
|
||||
tic = time.time()
|
||||
states = tree_search.run_batch(
|
||||
arguments, temperature=0, backend=backend, num_threads=args.parallel, progress_bar=True)
|
||||
arguments,
|
||||
temperature=0,
|
||||
backend=backend,
|
||||
num_threads=args.parallel,
|
||||
progress_bar=True,
|
||||
)
|
||||
latency = time.time() - tic
|
||||
answers_text = []
|
||||
for s in states:
|
||||
@@ -144,7 +157,7 @@ def main(args):
|
||||
"other": {
|
||||
"num_questions": args.num_questions,
|
||||
"parallel": args.parallel,
|
||||
}
|
||||
},
|
||||
}
|
||||
fout.write(json.dumps(value) + "\n")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user