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/hallusionbench_environment.py
View file

@ -7,10 +7,10 @@ import re
from typing import List, Optional, Tuple
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 HallusionBench(EvalBase):
@ -96,7 +96,9 @@ class HallusionBench(EvalBase):
return "Unknown"
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)
completion = await self.chat_completion(server, messages)
@ -140,4 +142,6 @@ class HallusionBench(EvalBase):
if __name__ == "__main__":
asyncio.run(eval_runner(HallusionBench(split="test", temperature=0.0, max_tokens=64)))
asyncio.run(
eval_runner(HallusionBench(split="test", temperature=0.0, max_tokens=64))
)