W4 attention surgery (0.1/0.3/0.6/0.8) - 27/30 instruction following 97d134b verified vdmbrsv commited on 3 days ago
Update weights: W4 attention surgery (stepped 0.1/0.3/0.6/0.8) - 27/30 instruction following 289b9e7 verified vdmbrsv commited on 3 days ago