gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-28 16:07:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: run benchmark on gpt-4o & llama 3.1 (#497)

Browse Source 
* Run benchmark on gpt-4o & llama 3.1

* update link
This commit is contained in:
you-n-g
2024-11-26 12:02:09 +08:00
committed by GitHub
parent d54e14f1d9
commit c3f78f8bce
7 changed files with 389 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/components/coder/factor_coder/eva_utils.py
+2 -6
View File
@@ -221,15 +221,11 @@ class FactorOutputFormatEvaluator(FactorEvaluator):
str(resp_dict["output_format_feedback"]),
resp_dict["output_format_decision"],
)
except json.JSONDecodeError as e:
raise ValueError("Failed to decode JSON response from API.") from e
except KeyError as e:
except (KeyError, json.JSONDecodeError) as e:
attempts += 1
if attempts >= max_attempts:
raise KeyError(
"Response from API is missing 'output_format_decision' or 'output_format_feedback' key after multiple attempts."
"Wrong JSON Response or missing 'output_format_decision' or 'output_format_feedback' key after multiple attempts."
) from e
return "Failed to evaluate output format after multiple attempts.", False