Only 8K context as well, like Mistral.
Also, as always, take these benchmarks with a huge grain of salt. Even base model releases are frequently (seemingly) contaminated these days.
Also, as always, take these benchmarks with a huge grain of salt. Even base model releases are frequently (seemingly) contaminated these days.
Mistral 7b instruct 0.2 is just a fine tune of Mistral 7b.
"Further, we filter all evaluation sets from our pre-training data mixture, run targeted contamination analyses to check against evaluation set leakage, and reduce the risk of recitation by minimizing proliferation of sensitive outputs."