David Tseng

First up, this library is amazing and works really well on mobile device. Unfortunately, I am stuck on a request to META-INFO/container.xml for a day. It only happens in cross...

max_seq_length and max_seq_len confusion

1

Hi team! Are these two `max_seq_length` and `max_seq_len` supposed to be the same parameter? https://github.com/princeton-nlp/MeZO/blob/552cb1b710767f9a6e1dc8f9645d7640376f9941/medium_models/run_fewshot.sh#L37 https://github.com/princeton-nlp/MeZO/blob/552cb1b710767f9a6e1dc8f9645d7640376f9941/medium_models/run_fewshot.sh#L91 Only `max_seq_length` is referenced in script. Not sure if its a bug.

magnetic one example failed with MultimodalWebSurfer is not defined

4

### What happened? While running example.py of magnetic one, "**Click** a button" step failed due to the following ``` Web surfing error: Traceback (most recent call last): File \"/autogen/python/packages/autogen-magentic-one/src/autogen_magentic_one/agents/multimodal_web_surfer/multimodal_web_surfer.py\", line...

incorrect causal mask in global attention

1

I am using GlobalAttention and got abnormally low loss even when I set causal to True. Upon inspection, I found the causal mask is not applied at all. Here the...