Models

AmberYifan/Llama-3.1-8B-sft-SPIN-gpt4o-beta0.8-lr1e-7

Text Generation • 8B • Updated May 30 • 8

AmberYifan/Llama-3.1-8B-sft-SPIN-gpt4o-beta0.9-lr1e-7

Text Generation • 8B • Updated May 30 • 7

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.3-lr5e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.1-lr1e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.3-lr1e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.2-lr5e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.2-lr1e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.4-lr5e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.4-lr1e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.5-lr5e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.6-lr5e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.7-lr5e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7

Text Generation • 8B • Updated May 30 • 7

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.9-lr5e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.5-lr1e-7

Text Generation • 8B • Updated May 30 • 5

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.6-lr1e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.7-lr1e-7

Text Generation • 8B • Updated May 30 • 5

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr1e-7

Text Generation • 8B • Updated May 30 • 6

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.9-lr1e-7

Text Generation • 8B • Updated May 30 • 9

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-ORPO

Text Generation • 8B • Updated May 31 • 12

AmberYifan/Llama-3.1-8B-sft-dpo-10k-ORPO

Text Generation • 8B • Updated May 31 • 8

AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-KTO

Text Generation • 8B • Updated May 31 • 8

AmberYifan/Llama-3.1-8B-sft-SPIN-gpt4o-ORPO

Text Generation • 8B • Updated May 31 • 9

AmberYifan/Llama-3.1-8B-sft-spin-10k-KTO

Text Generation • 8B • Updated May 31 • 8

AmberYifan/Llama-3.1-8B-sft-all-pool-ORPO

Text Generation • 8B • Updated May 31 • 13

AmberYifan/Llama-3.1-8B-sft-peers-pool-ORPO

Text Generation • 8B • Updated May 31 • 8

AmberYifan/Llama-3.1-8B-sft-dpo-10k-KTO

Text Generation • 8B • Updated May 31 • 6

AmberYifan/Llama-3.1-8B-sft-spin-10k-ORPO

Text Generation • 8B • Updated May 31 • 9

AmberYifan/Llama-3.1-8B-sft-SPIN-gpt4o-KTO

Text Generation • 8B • Updated May 31 • 8

AmberYifan/Llama-3.1-8B-sft-SPIN-Llama-3.1-70B-Instruct-KTO

Text Generation • 8B • Updated May 31 • 9