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

hopefully final linter fixes lol

Browse source
This commit is contained in:
teknium 2025-12-24 23:36:36 +00:00
parent 67869c3a79
commit 85296c519e
29 changed files with 76 additions and 155 deletions
Download patch file Download diff file Expand all files Collapse all files

5
environments/eval_environments/pubmedqa_eval.py
View file

@ -17,10 +17,8 @@ the gold standard (yes/no/maybe).
"""
import asyncio
import os
import random
import re
import time
from typing import Dict, List, Optional, Tuple
import wandb
@ -40,7 +38,6 @@ from atroposlib.envs.base import (
APIServerConfig,
BaseEnv,
BaseEnvConfig,
EvalHandlingEnum,
)
# Valid answers for PubMedQA
@ -48,7 +45,7 @@ VALID_ANSWERS = {"yes", "no", "maybe"}
# Prompt template for PubMedQA with answer tag instruction
PUBMEDQA_PROMPT_TEMPLATE = """Answer the following biomedical research question based on the provided context. Think step by step before answering.
PUBMEDQA_PROMPT_TEMPLATE = """Answer the following biomedical research question based on the provided context. Think step by step before answering. # noqa: E501
Provide your final answer within <answer></answer> tags, containing only one of: yes, no, or maybe.