stefaniancu/rost-73m-base
Updated • 8
rost-experiments
small-scale rost research checkpoints: 73M/126M/286M scaling, SFT and diacritics-handling ablations
-
-
stefaniancu/rost-73m-sft
Updated • 10 -
stefaniancu/rost-73m-en-baseline
Updated • 9 -
stefaniancu/rost-73m-diacritics-normalized
Updated • 9 -
stefaniancu/rost-73m-diacritics-stripped
Updated • 11 -
stefaniancu/rost-126m-base
Updated • 28 -
stefaniancu/rost-126m-sft
Updated • 9 -
stefaniancu/rost-126m-diacritics-raw
Updated • 10 -
stefaniancu/rost-126m-diacritics-normalized
Updated • 7 -
stefaniancu/rost-126m-diacritics-stripped
Updated • 12 -
stefaniancu/rost-286m-base
Updated • 8 -
stefaniancu/rost-286m-sft
Updated • 6 • 1 -
stefaniancu/rost-286m-diacritics-stripped
Updated • 11 -
stefaniancu/rost-d6-base
Updated -
stefaniancu/rost-d6-sft
Updated