RLAIF

community

AI & ML interests

None defined yet.

RLAIF 's datasets 134

RLAIF/dpo_answer_openorca_base_nathan_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Sep 2, 2025 • 65.3k • 11

RLAIF/dpo_answer_openorca_angel_base_nathan_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Sep 2, 2025 • 45.9k • 10

RLAIF/dpo_answer_openorca_angel_nathan_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Sep 2, 2025 • 65.3k • 14

RLAIF/dpo_answer_openorca_angel_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Sep 2, 2025 • 42.4k • 12

RLAIF/dpo_answer_openorca_openorca_argilla_rejudged_filtered_1e-6_0.02_1.7B_4B_with_gold_labels_kl_est

Viewer • Updated Aug 31, 2025 • 44.1k • 12

RLAIF/dpo_answer_openorca_skywork_rejudged_filtered_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 31, 2025 • 38.8k • 9

RLAIF/dpo_answer_openorca_baseline_mix_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 30, 2025 • 65.3k • 9

RLAIF/dpo_answer_openorca_openorca_argilla_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 30, 2025 • 60k • 12

RLAIF/dpo_answer_openorca_skywork_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 30, 2025 • 51.2k • 8

RLAIF/dpo_answer_openorca_helpsteer3_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 30, 2025 • 40.6k • 10

RLAIF/dpo_answer_openorca_ppe_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 30, 2025 • 37.1k • 11

RLAIF/dpo_thinking_openorca_offtheshelf_improved_1e-6_0.02_1.7B_0.6B_with_gold_labels_kl_estimation

Viewer • Updated Aug 30, 2025 • 141k • 10

RLAIF/dpo_answer_openorca_ultrafeedback_s3_lr1e6_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_est

Viewer • Updated Aug 29, 2025 • 65.3k • 10

RLAIF/dpo_answer_openorca_ultrafeedback_s100_lr1e6_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_est

Viewer • Updated Aug 29, 2025 • 65.3k • 11

RLAIF/dpo_answer_openorca_ultrafeedback_s336_lr1e5_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_est

Viewer • Updated Aug 29, 2025 • 58.2k • 11

RLAIF/dpo_thinking_openorca_offtheshelf_improved_1e-6_0.02_1.7B_8B_with_gold_labels_kl_estimation

Viewer • Updated Aug 29, 2025 • 152k • 6

RLAIF/dpo_answer_openorca_offtheshelf_improved_1e-6_0.02_1.7B_14B_with_gold_labels_kl_estimation

Viewer • Updated Aug 29, 2025 • 152k • 12

RLAIF/dpo_thinking_openorca_offtheshelf_improved_1e-6_0.02_1.7B_1.7B_with_gold_labels_kl_estimation

Viewer • Updated Aug 28, 2025 • 152k • 11

RLAIF/dpo_thinking_openorca_offtheshelf_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 28, 2025 • 152k • 10

RLAIF/dpo_answer_openorca_offtheshelf_improved_1e-6_0.02_1.7B_8B_with_gold_labels_kl_estimation

Viewer • Updated Aug 28, 2025 • 152k • 12

RLAIF/dpo_answer_openorca_offtheshelf_improved_1e-6_0.02_1.7B_4B_with_gold_labels_kl_estimation

Viewer • Updated Aug 28, 2025 • 152k • 11

RLAIF/dpo_answer_openorca_offtheshelf_improved_1e-6_0.02_1.7B_1.7B_with_gold_labels_kl_estimation

Viewer • Updated Aug 27, 2025 • 152k • 9

RLAIF/dpo_answer_openorca_offtheshelf_improved_1e-6_0.02_1.7B_0.6B_with_gold_labels_kl_estimation

Viewer • Updated Aug 27, 2025 • 152k • 12

RLAIF/dpo_uf_rejudged_mixed_openorca_with_gold_labels_kl_estimation

Viewer • Updated Aug 27, 2025 • 152k • 11

RLAIF/dpo_answer_2e-6_openorca_prompts_responses_1e-6_0.02_0.6B_0.6B_with_gold_labels_kl_estimation

Viewer • Updated Aug 23, 2025 • 86.5k • 10

RLAIF/dpo_uf_rejudged_mixed_openorca_kl_estimation

Viewer • Updated Aug 21, 2025 • 65.6k • 4

RLAIF/dpo_uf_rejudged_mixed_openorca_kl_est

Viewer • Updated Aug 21, 2025 • 65.6k • 4

RLAIF/dpo_answer_offtheshelf_openorca_1e-6_0.02_0.6B_0.6B_with_gold_labels_kl_estimation

Viewer • Updated Aug 21, 2025 • 49.4k • 10

RLAIF/dpo_answer_ultrafeedback_filtered_openorca_1e-6_0.02_0.6B_0.6B_with_gold_labels_kl_estimation

Viewer • Updated Aug 21, 2025 • 49.4k • 13

RLAIF/dpo_answer_ultrafeedback_openorca_1e-6_0.02_0.6B_0.6B_with_gold_labels_kl_estimation

Viewer • Updated Aug 21, 2025 • 49.4k • 10