lmarena.ai@lmarena_ai

3 years ago

[Arena Update] @cohere's Command R is now top-10 in Arena leaderboard🔥 It's now one of the best open models reaching the level of top proprietary models. We find the model great at handling longer context, which we plan to separate as a new category in Arena very soon.… https://t.co/ezIc5H6frM https://t.co/7AAOLO3emP

Sourcegraph@Sourcegraph

3 years ago

Experimental local chat with Cody and @ollama dropped a few weeks ago. Now you can run local inference for Cody Chat and Commands with any model pulled from Ollama. Happy hacking! Learn how 👇 https://t.co/PG4Znwul9D

TuringPost@TheTuringPost

3 years ago

While reward models (RMs) play a crucial role in AI alignment, their evaluation has been largely overlooked. A recent study introduced REWARDBENCH, a benchmark dataset and codebase designed to assess RMs across various tasks. 1/2 https://t.co/PFjzF6OS0p