NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-19 12:57:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[pre-commit.ci] auto fixes from pre-commit.com hooks

Browse source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2026-01-23 00:49:46 +00:00
parent 0a16fafadb
commit 655faa775c
27 changed files with 134 additions and 66 deletions
Download patch file Download diff file Expand all files Collapse all files

10
environments/eval_environments/vision_evals/wemath_environment.py
View file

@ -10,10 +10,10 @@ from typing import Dict, List, Tuple
import pandas as pd
from datasets import load_dataset
from environments.eval_environments.eval import EvalBase, eval_runner
from PIL import Image
from atroposlib.envs.server_handling.server_manager import ServerManager
from environments.eval_environments.eval import EvalBase, eval_runner
class WeMath(EvalBase):
@ -135,7 +135,9 @@ class WeMath(EvalBase):
return False
return prediction.upper() == answer.upper()
async def run_item(self, server: ServerManager, data_item: dict) -> Tuple[dict, dict]:
async def run_item(
self, server: ServerManager, data_item: dict
) -> Tuple[dict, dict]:
try:
messages = self.build_messages(data_item)
@ -365,5 +367,7 @@ def _compute_final_scores(total_counts: Dict, total_count: int = 525) -> Dict:
if __name__ == "__main__":
asyncio.run(
eval_runner(WeMath(split="testmini", use_cot=False, temperature=0.0, max_tokens=512))
eval_runner(
WeMath(split="testmini", use_cot=False, temperature=0.0, max_tokens=512)
)
)