LMSYS’ Chatbot Arena is widely regarded as one of, if not, the most reliable open benchmarks for LLMs. Real users provide prompts to chatbots and then blindly pick the best response. The only drawback is that the leaderboard is restricted to the most popular models and, even then, it can take a while for new models to be added. This is understandable given the considerable ongoing costs associated with... - Source: Hacker News / 4 months ago

I've recently updated the LLM Explorer (https://llm.extractum.io) - a directory that houses more than 13,000 LLMs. For those, who are new to the project: it offers a user-friendly interface for searching and filtering models by categories, comparing them and swiftly identifying superior alternatives (which is notably more convenient and faster than browsing HuggingFace). Source: 6 months ago

It's been some time since I announced LLM Explorer. I've taken into account all of your comments and feedback on the project, made the necessary fixes, and incorporated new features. Now, I'm excited to present the new version (v2.0) of the service: https://llm.extractum.io. Source: 7 months ago

The original link to the directory is llm.extractum.io. Thank you! Source: 10 months ago

MlOps is not just a hyped term,its a thing actually. I am a Mlops engineer working in a big firm setting up Mlops infrastructure pf clients.Machine learning is not only about training models and deploying them to get predictions.There are lot of problems which occurs in the models post production. As time passes,model do age as well the distribution of data on which the model is trained changes (data drift)... Source: 9 months ago