Model synced from source: jackf857/llama-3-8b-base-cpo-ultrafeedback-4xH200-batch-128-rerun
Updated 2026-05-09 21:05:41 +08:00
Model synced from source: jackf857/qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.85
Updated 2026-05-09 20:50:42 +08:00
Model synced from source: jackf857/llama-3-8b-base-orpo-ultrafeedback-4xh200-rerun
Updated 2026-05-09 20:44:36 +08:00
Model synced from source: jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.6
Updated 2026-05-09 12:28:09 +08:00
Model synced from source: jackf857/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.4
Updated 2026-05-09 11:52:40 +08:00
Model synced from source: jackf857/llama-3-8b-base-cpo-ultrafeedback-8xh200
Updated 2026-04-27 23:02:42 +08:00
Model synced from source: jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star0.6-4xh200-batch-64-20260421-214335-rerun
Updated 2026-04-27 09:47:43 +08:00
Model synced from source: jackf857/llama-3-8b-base-r-dpo-ultrafeedback-4xh200
Updated 2026-04-25 12:06:52 +08:00
Model synced from source: jackf857/llama-3-8b-base-margin-dpo-hh-4xh100
Updated 2026-04-24 16:00:03 +08:00
Model synced from source: jackf857/llama-3-8b-base-robust-dpo-ultrafeedback-8xh200
Updated 2026-04-24 02:33:42 +08:00
Model synced from source: jackf857/llama-3-8b-base-ipo-ultrafeedback-8xh200
Updated 2026-04-24 02:33:42 +08:00
Model synced from source: jackf857/llama-3-8b-base-kto-ultrafeedback-8xh200
Updated 2026-04-23 23:37:11 +08:00
Model synced from source: jackf857/llama-3-8b-base-simpo-8xh200
Updated 2026-04-23 23:03:39 +08:00
Model synced from source: jackf857/llama-3-8b-base-slic-hf-ultrafeedback-4xh200
Updated 2026-04-23 22:59:09 +08:00
Model synced from source: jackf857/llama-3-8b-base-margin-dpo-hh-harmless-batch-size-64
Updated 2026-04-21 14:03:12 +08:00