NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-22 16:48:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

fix: correct dataset name to bigcode/humanevalpack

Browse source
This commit is contained in:
RUFFY-369 2026-03-24 15:32:25 +05:30
parent 590e8a1ef2
commit 5c2afa8ea7
2 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

8
environments/community/code_debug_env/code_debug_env.py
View file

@ -2,7 +2,7 @@
Code Debug Environment for Atropos
Trains LLMs to debug and fix buggy Python functions.
Uses the HumanEvalFix dataset with execution-based verification
Uses the HumanEvalPack dataset (HumanEvalFix subset) with execution-based verification
against ground-truth test cases.
Environment pattern follows sql_query_env for consistency.
@ -162,11 +162,11 @@ class CodeDebugEnv(BaseEnv):
await super().wandb_log(wandb_metrics)
async def setup(self):
"""Load the HumanEvalFix dataset and prepare train/test splits."""
"""Load the HumanEvalPack dataset (HumanEvalFix) and prepare train/test splits."""
from datasets import load_dataset
print("Loading HumanEvalFix dataset...")
dataset = load_dataset("bigcode/humanevalfix-python", split="test")
print("Loading HumanEvalPack (python) dataset...")
dataset = load_dataset("bigcode/humanevalpack", "python", split="test")
all_items: List[CodeDebugItem] = []
for row in dataset: