Sachin Iyer

sachiniyer 's models 60

Sort:  Recently updated

sachiniyer/Qwen2.5-1.5B-DPO-Diverse-Schwinn-v32

Text Generation • 2B • Updated Feb 19 • 7

sachiniyer/Qwen2.5-1.5B-DPO-Diverse-Schwinn-v31

Text Generation • 2B • Updated Feb 19 • 2

sachiniyer/Qwen2.5-1.5B-DPO-Diverse-Schwinn-v30

Text Generation • 2B • Updated Feb 16 • 2

sachiniyer/Qwen2.5-1.5B-DPO-Diverse-Schwinn-v29

Text Generation • 2B • Updated Feb 16 • 1

sachiniyer/Qwen2.5-1.5B-DPO-Diverse-Schwinn-v28

Text Generation • 2B • Updated Feb 12 • 1

sachiniyer/Qwen2.5-1.5B-DPO-Diverse-Schwinn-v27

Text Generation • 2B • Updated Feb 6

sachiniyer/Qwen2.5-1.5B-GRPO-LowLR-Schwinn-v24

Text Generation • 2B • Updated Feb 5 • 2

sachiniyer/Qwen2.5-1.5B-HardPromptSFT-Schwinn-v26

Text Generation • 2B • Updated Feb 5 • 1

sachiniyer/Qwen2.5-1.5B-GRPO-Iterative-Schwinn-v25

Text Generation • 2B • Updated Feb 5 • 2

sachiniyer/Qwen2.5-1.5B-GRPO-PeakCapture-Schwinn-v21

Text Generation • 2B • Updated Feb 4 • 2

sachiniyer/Qwen2.5-1.5B-GRPO-Merged-Schwinn-v22

Text Generation • 2B • Updated Feb 4 • 1

sachiniyer/Qwen2.5-1.5B-GRPO-HighKL-Scaled-Schwinn-v19

Text Generation • 2B • Updated Feb 4

sachiniyer/Qwen2.5-1.5B-GRPO-HighKL-Schwinn-v16

Text Generation • 2B • Updated Feb 3

sachiniyer/Qwen2.5-1.5B-GRPO-EarlyStop-Schwinn-v20

Text Generation • 2B • Updated Feb 3 • 1

sachiniyer/Qwen2.5-1.5B-GRPO-NegReward-Schwinn-v17

Text Generation • 2B • Updated Feb 3 • 2

sachiniyer/Qwen2.5-1.5B-GRPO-Count-Schwinn-v15

Text Generation • 2B • Updated Feb 3

sachiniyer/Qwen2.5-1.5B-GRPO-Count-Schwinn-v12

Text Generation • 2B • Updated Feb 3 • 1

sachiniyer/Qwen2.5-1.5B-GRPO-Count-Schwinn-v10

Text Generation • 2B • Updated Feb 2

sachiniyer/Qwen2.5-1.5B-RejectionSFT-Schwinn-v9

Text Generation • 2B • Updated Jan 23

sachiniyer/Qwen2.5-1.5B-GRPO-Schwinn-v8

Text Generation • 2B • Updated Jan 23 • 1

sachiniyer/Qwen2.5-1.5B-SFT-Schwinn-v7-diverse-v2

Text Generation • 2B • Updated Jan 23

sachiniyer/Qwen2.5-1.5B-SFT-Schwinn-v7-diverse

Text Generation • 2B • Updated Jan 22 • 1

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v9

Text Generation • 2B • Updated Jan 21

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v8

Text Generation • 2B • Updated Jan 21

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

Text Generation • 2B • Updated Jan 21 • 2 •

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v6

Text Generation • 2B • Updated Jan 21 • 1

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v5

Text Generation • 2B • Updated Jan 21

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v4

Text Generation • 2B • Updated Jan 21 • 2

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v3

Text Generation • 2B • Updated Jan 20

sachiniyer/Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v2

Text Generation • 2B • Updated Jan 20 • 3