Meet Reka Core, our best and most capable multimodal language model yet. 🔮 It’s been a busy few months training this model and we are glad to finally ship it! 💪 Core has a lot of capabilities, and one of them is understanding video --- let’s see what Core thinks of the 3 body trailer.👇
We evaluate Core on standard benchmarks for both text and multimodal, along with a blind third-party human evaluation.
Along with Core, we have published a technical report detailing the training, architecture, data, and evaluation for the Reka models. publications.reka.ai/reka-core-tech…
See some examples of outputs from Core in showcase.reka.ai, or try it yourself on chat.reka.ai.
@RekaAILabs in the technical report "in comparsion with GPT4-V, Claude 3, Gemini Pro, IDEFICS 80B, Adept Fuyu 8B, and the strongest Llava 1.6B model"--seems "the strongest Llava 1.6B model" should be "the strongest Llava 1.6 (34B) model".