Holarissun/dpo_helpful_gemmaneghelpful_contrast64_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 Updated 24 days ago
Holarissun/dpo_tldrtldr_contrast_subset10000_modelgemma2b_maxsteps5000_bz8_lr5e-06 Updated 24 days ago
Holarissun/dpo_tldrtldr_contrast_subset10000_modelgemma2b_maxsteps5000_bz8_lr1e-06 Updated 24 days ago
Holarissun/dpo_helpful_gemmaneghelpful_contrast128_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 Updated 24 days ago
Holarissun/dpo_helpful_gemmaneghelpful_contrast128_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 Updated 24 days ago
Holarissun/dpo_helpful_gemmaneghelpful_contrast64_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 Updated 24 days ago