tan90º
Hello, I encountered a runtime error when using the live demo on HuggingFace Space. The error message is as follows: ## error message ### Runtime error failed to create containerd...
 I wanted to visualize how the model action on the Mind2Web dataset, but SeeAct didn't seem to do that. When computing online, the output "success_or_not" is always empty, which...
I've been using guidance to evaluate a dataset recently, but guidance can only handle one input at a time, which is really slow, and I was wondering if support for...
**Describe the bug** 我在使用gpt-3.5-turbo复现AgentBench中的mind2web(m2w)时，注意到有35%的结果为unknown，在`runs.jsonl`中，这35%的unknown结果没有任何的输出。 原以为是自己的问题，但注意到我复现出的分数与论文中的分数近乎一致（原论文20分，我的23分），所以这应该是AgentBench本身的问题，希望作者能修复这个unknown。 **Screenshots or Terminal Copy&Paste**    **Desktop (please complete the following information):** - OS: windows11 + WSL2(Ubuntu) + Docker