Xingyao Wang
50c13aad98
[Eval] Improve SWE-Bench Eval harness: multi-run support & entry script simplification (#4396)
|
пре 1 година | |
|---|---|---|
| .. | ||
| .cache_program | пре 1 година | |
| scripts | пре 1 година | |
| Dockerfile | пре 1 година | |
| README.md | пре 1 година | |
| __init__.py | пре 1 година | |
| instruction.txt | пре 1 година | |
| logic_inference.py | пре 1 година | |
| run_infer.py | пре 1 година | |
README.md
Logic Reasoning Evaluation
This folder contains evaluation harness for evaluating agents on the logic reasoning benchmark ProntoQA and ProofWriter.
Setup Environment and LLM Configuration
Please follow instruction here to setup your local development environment and LLM.
Run Inference on logic_reasoning
The following code will run inference on the first example of the ProofWriter dataset,
./evaluation/logic_reasoning/scripts/run_infer.sh eval_gpt4_1106_preview_llm ProofWriter