We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent a9c1e4a commit f897bf4Copy full SHA for f897bf4
src/inspect_evals/swe_bench/README.md
@@ -12,7 +12,7 @@ Contributed by [@max-kaufmann](https://github.com/max-kaufmann)
12
First, install the `inspect_ai` and `inspect_evals` Python packages with:
13
```bash
14
pip install inspect_ai
15
-pip install inspect_evals[swe_bench]@git+https://github.com/UKGovernmentBEIS/inspect_evals
+pip install "inspect_evals[swe_bench]@git+https://github.com/UKGovernmentBEIS/inspect_evals"
16
```
17
18
Then, evaluate against one or more models with:
@@ -155,4 +155,4 @@ python -m swebench.harness.run_evaluation \
155
--predictions_path path-to-outputs \
156
--max_workers 4 \
157
--run_id check-outputs
158
-```
+```
0 commit comments