llm-scripts / scripts /yans /eval /lm-evaluation-harness /tests /testdata /blimp_causative-v0-res.json
| {"results": {"blimp_causative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_causative": 0}} |
| {"results": {"blimp_causative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_causative": 0}} |