liminerity

/

Blurstral-7b-slerp

like 1

Please do. It is annoying having to filter out models like yours when looking at the leaderboard. You are degrading the leaderboard by obfuscating its objective reliability. This is NOT a "pretrained" model as defined by the leaderboard with "new, base models, trained on a given text corpora using masked modelling". Instead, this is a merged model, so please categorize it as such.
See also https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/629