transformers-CFG VS autogen

Does it support constrained generation during training?

This is what we need for the large language models I am training for health care use cases.

For example, constraining LLM output is currently done by masking, and having this rust based library would enable novel ways to train LLMs.

Relevant papers:

https://github.com/epfl-dlab/transformers-CFG

https://neurips.cc/virtual/2023/poster/70782

AutoGen is an AI framework by Microsoft designed to streamline multi-agent conversations. AutoGen allows agents to communicate, share information, and make collective decisions. This setup enhances the responsiveness and dynamism of conversations. Developers use AutoGen to tailor agents to specific roles, such as programmer, content writer, CEO, etc. This enhances their ability to handle tasks from simple queries to intricate problem-solving.

I am still playing around with the project but FYI, the parsing for the github repo URL at https://glide.agenticlabs.com/ will fail if there's a trailing slash in the repo link i.e. https://github.com/microsoft/autogen/ won't work but https://github.com/microsoft/autogen will.

New example notebook demoing video transcript translate with whisper.

New release: v0.2.1

I disagree with the conclusion. In software, I've seen 10x engineers in person and I don't think they're replaceable. Whereas, the new college grad or that entry level dev who doesn't design anything and just writes small amounts of code, doing exactly as told is replaceable by an AI. Frameworks similar to Microsoft Autogen(https://github.com/microsoft/autogen) can in theory build agents who can do these tasks with ease whereas a 10x engineer can focus on directing the agents and designing systems.

Microsoft autogen

CompressibleAgent (experimental) can be used to handle long conversations. Notebook: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_compression.ipynb