jackfeng

jackf857 's models 134

Sort:  Recently updated

jackf857/Qwen3-8b-ultrafeedback-binarized-e-dpo

Text Generation • 8B • Updated Mar 10 • 1

jackf857/Qwen-8b-sft-hh-harmless-base-e-dpo

Text Generation • 8B • Updated Mar 9 • 2

jackf857/Qwen-8b-sft-hh-helpful-base-e-dpo

Text Generation • 8B • Updated Mar 9 • 1

jackf857/Llama-8b-sft-hh-harmless-base-e-dpo

Text Generation • 8B • Updated Mar 9 • 1

jackf857/Llama-8b-sft-hh-helpful-base-e-dpo

Text Generation • 8B • Updated Mar 8 • 1

jackf857/llama3-instruct-edpo

8B • Updated Feb 18 • 1

jackf857/llama32-8b-dpo-hh-beta0.5

Updated Jan 31

jackf857/llama32-1b-dpo-hh

1B • Updated Jan 17

jackf857/llama32-1b-dynamic-dpo-hh

1B • Updated Jan 17

jackf857/llama32-1b-dpo-hh-rollout

1B • Updated Jan 17

jackf857/llama32-1b-dynamic-dpo-hh-rollout

1B • Updated Jan 17 • 3

jackf857/Llama32-1b-Instruct-hh-sft-30

1B • Updated Jan 16 • 1

jackf857/llama32-1b-og-dpo-hh

1B • Updated Jan 12 • 1

jackf857/canton_fine-tuned_qwen3b-instruct

Updated Apr 23, 2025