github/OpenHands
1
1
Fork 0
mirror of https://github.com/All-Hands-AI/OpenHands.git synced 2026-01-09 23:08:04 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat(evaluation): Added INSTRUCTION_TEMPLATE_NAME to run_infer.py in swe_bench (#10270)

Browse Source 
Co-authored-by: Xingyao Wang <xingyao@all-hands.dev>
Co-authored-by: mamoodi <mamoodiha@gmail.com>
This commit is contained in:
Kevin Musgrave
2025-08-18 07:18:08 -07:00
committed by GitHub
parent bef6b1afee
commit 74ba21bad0
3 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
evaluation/benchmarks/swe_bench/run_infer.py
View File

@@ -108,7 +108,9 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
llm_model = metadata.llm_config.model
# Determine the template file based on mode and LLM
if mode.startswith('swt'):
if metadata.instruction_template_name:
template_name = metadata.instruction_template_name
elif mode.startswith('swt'):
template_name = 'swt.j2'
elif mode == 'swe':
if 'gpt-4.1' in llm_model:
@@ -122,6 +124,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
logger.error(f'Unexpected evaluation mode: {mode}. Falling back to default.')
template_name = 'swe_default.j2'
logger.debug(f'Using instruction template file: {template_name}')
# Set up Jinja2 environment
# Assuming templates are in 'evaluation/benchmarks/swe_bench/prompts' relative to this script
prompts_dir = os.path.join(os.path.dirname(__file__), 'prompts')