I want to clarify something. Reranker is a general term that can refer to any model used for reranking. It is independent of implementation.

What you refer to

because reranker models look at the two pieces of content simultaneously and can be fine tuned to the domain in question. They shouldn’t be used for the initial retrieval because the evaluation time is O(n²) as each combination of input

Is a specific implementation known as CrossEncoder that is common for reranking models but not retrieval ones for the reasons you described. But you can also use any other architecture

On god

Thumbnail looks a little odd when small. You may want to go for a more digital llama aesthetic

autotracers can’t generate svgs from text

Claude frequently draws svgs to illustrate things for me (I’m guessing it’s in the prompt) but even though it’s better at it than all the other models, it still kinda sucks. It’s just fudamentally dumb task to do for a purely language model, similar to the arc-agi benchmark , just makes more sense for a vision model and trying to get an llm to do is a waste

what is the license? The link on hf just 404s

Very similar to chain of draft but seems more thorough

More info here https://www.reka.ai/news/introducing-reka-flash
HF: https://huggingface.co/RekaAI/reka-flash-3

It matches R1 in the given benchmarks. R1 has 671B params (36 activated) while this only has 32

insane, absolutely insane