zhengbang0707/Qwen3.5-9B-eSFT2-KL-a0.1-lr5e-5-utility250-talos-20260925T011728Z
Image-Text-to-Text • 9B • Updated • 10
Zhengbang Yang
zhengbang0707
AI & ML interests
None yet
Recent Activity
published a model about 2 months ago
zhengbang0707/Qwen3.5-9B-eSFT2-KL-a0.1-lr5e-5-utility250-talos-20260925T011728Z updated a model about 2 months ago
zhengbang0707/Qwen3.5-9B-eSFT2-KL-a0.1-lr5e-5-utility250-talos-20260925T011728Z published a model 4 months ago
zhengbang0707/satimp_raw_retention_beta1_0_beta2_5.5_lr_5e-6_epoch_1Organizations
zhengbang0707/satimp_raw_beta1_0.0_beta2_5.5_lr_5e-6_epoch_1
2B • Updated • 2
zhengbang0707/satimp_raw_retention_beta1_0_beta2_5.5_lr_5e-6_epoch_1
2B • Updated • 3
zhengbang0707/WGA_raw_beta_7_lr_5e-6_epoch_1
2B • Updated • 3
zhengbang0707/WGA_raw_retention_beta_7_lr_5e-6_epoch_1
2B • Updated • 1
zhengbang0707/Qwen3.5-9B-meSFT
Image-Text-to-Text • 9B • Updated • 10
zhengbang0707/Qwen3.5-9B-eSFT
Image-Text-to-Text • 9B • Updated • 5
zhengbang0707/Qwen3.5-9B-posthoc
Image-Text-to-Text • 9B • Updated • 6
zhengbang0707/FLAT_lr_1e-5_epoch_10
3B • Updated • 3
zhengbang0707/HP_SimNPO_beta_4_lr_5e-6_epoch_20
3B • Updated • 2
zhengbang0707/cyber_TWISE_gather_shift_ref_beta1.75
Text Generation • 7B • Updated • 3
zhengbang0707/cyber_npo_gather_shift_ref_beta0.1
Text Generation • 7B • Updated • 2
zhengbang0707/cyber_TWISE_gather_shift_beta1.75
Text Generation • 7B • Updated • 1
zhengbang0707/books_TWISE2_ref_top3_beta0.75
Updated
zhengbang0707/books_TWISE3_ref_top3_beta0.75
Updated
zhengbang0707/cyber_npo_gather_shift_beta0.1
Text Generation • 7B • Updated • 4
zhengbang0707/books2_npo_gather_shift
Text Generation • 3B • Updated • 4
zhengbang0707/cyber_npo_gather_shift
Text Generation • 7B • Updated • 4
zhengbang0707/cyber_TWISE_gather_shift_beta2.5
Text Generation • 7B • Updated • 2
zhengbang0707/cyber_TWISE_gather_shift_beta2
Text Generation • 7B • Updated • 3
zhengbang0707/cyber_TWISE2_top3_beta0.75
Text Generation • 7B • Updated • 4
zhengbang0707/books_TWISE3_top3_beta0.5
Text Generation • 7B • Updated • 2
zhengbang0707/books_TWISE3_top3_beta0.75
Text Generation • 7B • Updated • 3
zhengbang0707/books_TWISE2_top3_beta0.75
Text Generation • 7B • Updated • 7
zhengbang0707/books_TWISE2_top3_beta1.2
Text Generation • 7B • Updated • 2
zhengbang0707/books_TWISE2_top3_beta1.15
Text Generation • 7B • Updated • 5
zhengbang0707/books_TWISE2_top3_beta1.1
Text Generation • 7B • Updated • 2
zhengbang0707/books_TWISE2_top3_beta1
Text Generation • 7B • Updated • 7
zhengbang0707/books_TWISE2_top3_beta1.25
Text Generation • 7B • Updated • 4
zhengbang0707/books_TWISE2_top3_beta1.5
Text Generation • 7B • Updated • 3