Direct Preference Optimization Datasets - a davanstrien Collection

ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized_instruction_following

Viewer • Updated Jun 12, 2024 • 60.9k • 35 • 3

ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized_honesty

Viewer • Updated Jun 12, 2024 • 60.9k • 33

HuggingFaceH4/testing_h4

Viewer • Updated Sep 22, 2024 • 70 • 70

yitingxie/rlhf-reward-datasets

Viewer • Updated Jan 1, 2023 • 81.4k • 808 • 63

Baidicoot/augmented_advbench_v4

Viewer • Updated May 7, 2024 • 4.95k • 30

sfanm/ultrafeedback_llama3_label

Viewer • Updated Jun 13, 2024 • 60k • 31

HuggingFaceH4/summarize_from_feedback

Viewer • Updated Mar 11, 2024 • 353k • 40 • 3

HuggingFaceH4/orca_dpo_pairs

Viewer • Updated Apr 14, 2024 • 12.9k • 115 • 25

zhengr/ultrafeedback_binarized

Viewer • Updated Nov 8, 2023 • 190k • 96 • 2

trl-internal-testing/hh-rlhf-trl-style

Viewer • Updated Mar 13, 2024 • 169k • 435 • 11

HuggingFaceH4/cai-conversation-harmless

Viewer • Updated Feb 2, 2024 • 44.8k • 182 • 15

HuggingFaceH4/rlaif-v_formatted

Viewer • Updated Jul 2, 2024 • 83.1k • 495 • 8

nz/anthropic_hh_rlhf

Viewer • Updated Mar 19, 2024 • 169k • 31

trl-internal-testing/sentiment-trl-style

Viewer • Updated Aug 6, 2024 • 5.48k • 125

SAGI-1/Greetings_DPO_dataset_V1

Viewer • Updated Dec 18, 2023 • 891 • 36 • 3

trl-internal-testing/tldr-preference-trl-style

Viewer • Updated Jun 25, 2024 • 179k • 4.6k • 4

xinlai/Math-Step-DPO-10K

Viewer • Updated Jul 4, 2024 • 10.8k • 731 • 46

ContextualAI/ultrafeedback_binarized_1percent

Viewer • Updated May 13, 2024 • 200 • 123

arcee-ai/distilabel-intel-orca-dpo-pairs-binarized

Viewer • Updated May 18, 2024 • 12.9k • 3.49k • 1

Syed-Hasan-8503/orpo-40k-train-test

Viewer • Updated Jun 3, 2024 • 44.2k • 34

maywell/ko_Ultrafeedback_binarized

Viewer • Updated Nov 9, 2023 • 62k • 64 • 29

sfanm/ultrafeedback_llama3_pad_rm

Viewer • Updated Jun 9, 2024 • 56.4k • 35

mnoukhov/openai_summarize_comparisons_tldrprompt_relabel1b

Viewer • Updated Dec 2, 2023 • 97.5k • 32

Synadapt/Orpo_Split_Turns_v1_clean_ready

Viewer • Updated Jun 14, 2024 • 8.1k • 29

HuggingFaceH4/h4-tests-format-dpo-dataset

Viewer • Updated Mar 10, 2024 • 1 • 29

when2rl/tldr-summarisation-preferences_reformatted

Viewer • Updated May 9, 2024 • 177k • 29

alvarobartt/dpo-mix-7k-simplified

Viewer • Updated Mar 26, 2024 • 7.5k • 45 • 11

mlabonne/orpo-dpo-mix-40k-flat

Viewer • Updated Jun 7, 2024 • 44.2k • 92 • 11

valerielucro/gsm8k_preference_dataset

Viewer • Updated Jun 19, 2024 • 895 • 34 • 1

cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental

Viewer • Updated Aug 15, 2024 • 29.2k • 110 • 19

allenai/preference-test-sets

Viewer • Updated Mar 14, 2024 • 43.2k • 394 • 22

pharaouk/ultrafeedback-binarized-preferences-cleaned

Viewer • Updated Apr 5, 2024 • 60.9k • 69

smangrul/ultrachat-feedback-10k-chatml

Viewer • Updated Jan 27, 2024 • 12k • 33

yuasosnin/imdb-dpo

Viewer • Updated Dec 11, 2023 • 10k • 44

beyond/rlhf-reward-single-round-trans_chinese

Viewer • Updated Jul 5, 2023 • 24.9k • 63 • 37

Katayoon/SELM-Zephyr-7B-dataset

Viewer • Updated Jul 18, 2024 • 51.8k • 34

Magpie-Align/Magpie-Pro-DPO-200K

Viewer • Updated Aug 20, 2024 • 207k • 34 • 6

trl-internal-testing/mlabonne-chatml-dpo-pairs-copy

Viewer • Updated Jan 11, 2024 • 12.9k • 33

gx-ai-architect/HelpSteer2_DPO

Viewer • Updated Jun 24, 2024 • 7.59k • 30 • 1

when2rl/UltraFeedback_binarized_cleaned_annotated

Viewer • Updated Apr 17, 2024 • 62.7k • 42

youjunhyeok/ko-orca-pair-and-ultrafeedback-dpo

Viewer • Updated May 22, 2024 • 72.5k • 34 • 2

xiaodongguaAIGC/awesome-dpo

Viewer • Updated Jul 3, 2024 • 302k • 47 • 3

banghua/tldr_reward_model_labeled

Viewer • Updated Sep 21, 2023 • 176k • 39

pythainlp/oasst2_dpo_pairs_enth

Viewer • Updated Jun 16, 2024 • 5.28k • 41 • 1

YYYYYYibo/ultrafeedback_binarized_with_response_full_part0

Viewer • Updated Jul 17, 2024 • 20k • 30

ZhangShenao/gc_binarized_ultrafeedback

Viewer • Updated Jul 8, 2024 • 109k • 27

dinaaaaaa/lima_rand_sel_50_preference

Viewer • Updated Mar 29, 2024 • 500 • 28

argilla/OpenHermesPreferences

Viewer • Updated Mar 1, 2024 • 989k • 665 • 202

kira/math-dpo

Viewer • Updated Jul 2, 2024 • 2.42k • 38 • 7

kaist-ai/Multifaceted-Collection-DPO

Viewer • Updated Jul 1, 2024 • 65.1k • 85 • 8

YYYYYYibo/ultrafeedback_binarized_with_response_full_part1

Viewer • Updated Jul 17, 2024 • 20k • 30

princeton-nlp/llama3-ultrafeedback-armorm

Viewer • Updated Jul 18, 2024 • 61.8k • 286 • 16

mnoukhov/summarize_from_feedback_oai_preprocessing_1706381144_relabel_pythia6.9b

Viewer • Updated Jun 20, 2024 • 177k • 33

yaswanthchittepu/ultrafeedback-binarized-standard-margin-data-full

Viewer • Updated Jul 7, 2024 • 63.7k • 31

mnoukhov/summarize_from_feedback_oai_preprocessing_1706381144_relabel_pythia1b

Viewer • Updated May 16, 2024 • 177k • 29

nebchi/kor-orpo

Viewer • Updated Jun 18, 2024 • 98.1k • 33 • 1

wenbopan/Chinese-dpo-pairs

Viewer • Updated Apr 2, 2024 • 10.7k • 84 • 39

abhayesian/augmented_advbench_v5

Viewer • Updated Jul 5, 2024 • 4.95k • 61

aklein4/tldr-feedback

Viewer • Updated Jun 26, 2024 • 179k • 31

BramVanroy/ultra_feedback_dutch

Viewer • Updated 29 days ago • 53.6k • 61 • 2

yaswanthchittepu/ultrafeedback-binarized-pop-margin-data-full

Viewer • Updated Jul 7, 2024 • 63.7k • 32

RAY2L/llama3-ultrafeedback-mini

Viewer • Updated Jun 21, 2024 • 1.2k • 40

David-Xu/astronomy-stack-dpo-text

Viewer • Updated Mar 8, 2024 • 19.9k • 44 • 2

GitBag/multiturn-hh-turn-1-5

Viewer • Updated Jun 13, 2024 • 162k • 68

yhavinga/orpo-dpo-mix-dutch-40k

Viewer • Updated Jul 4, 2024 • 43.1k • 37 • 2

HuggingFaceH4/grok-conversation-harmless

Viewer • Updated Feb 2, 2024 • 44.8k • 48 • 23

rajj0/god_sent_datav1

Viewer • Updated Jun 5, 2024 • 2.84k • 30

GrowingApple/orpo_kor_translated_medical

Viewer • Updated Jun 12, 2024 • 10.4k • 30 • 3

trl-internal-testing/Anthropic-hh-rlhf-processed

Viewer • Updated Mar 13, 2024 • 3k • 36

GitBag/multiturn-512-hh-turn-1-5

Viewer • Updated Jun 28, 2024 • 165k • 45 • 1

snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset

Viewer • Updated Jan 23, 2024 • 62.7k • 77 • 42

maywell/ko_Ultrafeedback_binarized_10k

Viewer • Updated Nov 4, 2023 • 10k • 31 • 5

YYYYYYibo/ultrafeedback_binarized_with_response_full_part2

Viewer • Updated Jul 17, 2024 • 21.1k • 35

trl-internal-testing/descriptiveness-trl-style

Viewer • Updated Aug 6, 2024 • 5.42k • 44 • 1

mnoukhov/summarize_from_feedback_oai_preprocessing_1706381144

Viewer • Updated May 13, 2024 • 179k • 30

AlpacaAAR/epfl-synthetic-dpo

Viewer • Updated Jun 12, 2024 • 19.6k • 32

justinphan3110/toxic-dpo-v0.2-sft

Viewer • Updated May 29, 2024 • 540 • 30

minkyungpark/UFB_test_500

Viewer • Updated Jul 4, 2024 • 500 • 33

kaist-ai/Multifaceted-Collection-ORPO

Viewer • Updated Jul 1, 2024 • 64.6k • 42 • 10

orpo-explorers/OpenHermesPreferences-10k

Viewer • Updated Mar 30, 2024 • 10k • 31 • 2

when2rl/SHP_reformatted

Viewer • Updated May 27, 2024 • 386k • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_1

Viewer • Updated May 20, 2024 • 20k • 31

VictorDCh/spider-dpo-dataset

Viewer • Updated Jul 1, 2024 • 901 • 37

when2rl/Nectar_reformatted

Viewer • Updated Jun 5, 2024 • 183k • 38

lightblue/mitsu_full_borda

Viewer • Updated May 30, 2024 • 2.85k • 34 • 2

ibivibiv/cleaned_orca_math_dpo_pairs

Viewer • Updated May 24, 2024 • 200k • 53 • 2

when2rl/PKU-SafeRLHF_reformatted_filtered

Viewer • Updated May 27, 2024 • 136k • 28

IlyaGusev/saiga_preferences

Viewer • Updated Oct 28, 2024 • 30.6k • 69 • 4

Baidicoot/anthropic-harmless-rlhf

Viewer • Updated May 10, 2024 • 42.5k • 31

tasksource/tasksource_dpo_pairs

Viewer • Updated Jul 1, 2024 • 5.13M • 120 • 21

reciprocate/ultrafeedback_orca_math_dpo

Viewer • Updated Jan 8, 2024 • 73.8k • 33 • 1

zaddyzaddy/randomcrawl

Viewer • Updated Jun 15, 2024 • 100k • 29

abacusai/MetaMath_DPO_FewShot

Viewer • Updated Feb 26, 2024 • 395k • 89 • 25

Baidicoot/hh-rlhf-golden-harmful

Viewer • Updated May 10, 2024 • 7.64k • 31 • 1

We-Want-GPU/Yi-Ko-DPO-dataset

Viewer • Updated Dec 9, 2023 • 4k • 32 • 4

wisenut-nlp-team/dpo_test2

Viewer • Updated Jun 11, 2024 • 100 • 31

tasksource/oasst2_pairwise_rlhf_reward

Viewer • Updated Jan 9, 2024 • 28.4k • 44 • 2

reciprocate/dpo_ultra-capybara-code_filtered-best

Viewer • Updated Mar 19, 2024 • 35.2k • 31 • 1

Baidicoot/anthropic-hh-rlhf

Viewer • Updated May 10, 2024 • 169k • 33

when2rl/distilabel-intel-orca-dpo-pairs_cleaned_reformatted

Viewer • Updated Apr 17, 2024 • 12.8k • 31

JamesSpray/dpo_dataset_hh

Viewer • Updated Jul 14, 2024 • 24.2k • 30

kaitchup/UltraFeedback-prompt-chosen-rejected

Viewer • Updated Oct 23, 2023 • 18k • 48 • 6

rajj0/god_sent_data_v2

Viewer • Updated Jun 9, 2024 • 2.84k • 32

arham6/dataset3

Viewer • Updated Jun 25, 2024 • 258 • 39

gabjp/PKU-safe-dpo

Viewer • Updated Jun 28, 2024 • 75.1k • 31

Windy/tmp_output

Viewer • Updated Jun 30, 2024 • 60 • 32

Columbia-NLP/DPO-HelpSteer

Viewer • Updated Jul 10, 2024 • 9.17k • 36

NobodyExistsOnTheInternet/ToxicDPOqa

Viewer • Updated Apr 26, 2024 • 6.87k • 48 • 16

sfanm/ultrafeedback_llama3

Viewer • Updated Jun 12, 2024 • 60.2k • 32

when2rl/distilabel-capybara-dpo-7k-binarized_reformatted

Viewer • Updated Apr 17, 2024 • 7.56k • 44

when2rl/py-dpo-v0.1_reformatted

Viewer • Updated Apr 17, 2024 • 9.47k • 29

ineskoder/KIBRAM_dataset

Viewer • Updated May 29, 2024 • 72.2k • 31

alexredna/oasst2_dpo_pairs

Viewer • Updated Jul 17, 2024 • 10k • 53 • 6

mintaeng/dpo_ko_mj

Viewer • Updated Jun 18, 2024 • 3k • 36

abacusai/ARC_DPO_FewShot

Viewer • Updated Feb 26, 2024 • 4.25k • 63 • 17

2A2I/Aya-Command.R-DPO

Viewer • Updated May 16, 2024 • 14.2k • 30 • 7

pgurazada1/ultrafeedback-sample

Viewer • Updated Jul 2, 2024 • 315 • 49

when2rl/HelpSteer_reformatted

Viewer • Updated May 27, 2024 • 9.17k • 34

YYYYYYibo/full_simple_online_train_part_2

Viewer • Updated Jul 4, 2024 • 19k • 28

YYYYYYibo/full_simple_online_train_part_3

Viewer • Updated Jul 4, 2024 • 19.3k • 30

YYYYYYibo/gshf_vllm_1_part_2

Viewer • Updated Jul 5, 2024 • 20k • 31

YYYYYYibo/gshf_vllm_2_part_2

Viewer • Updated Jul 5, 2024 • 20k • 29

YYYYYYibo/gshf_train_part_2

Viewer • Updated Jul 5, 2024 • 20k • 29

YYYYYYibo/gshf_vllm_2_part_3

Viewer • Updated Jul 5, 2024 • 21.1k • 30

lca0503/ultrafeedback-binarized-preferences-cleaned

Viewer • Updated Jul 8, 2024 • 60.9k • 28

We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs

Viewer • Updated Dec 18, 2023 • 12.7k • 57 • 5

lightblue/mitsu_tophalf_borda

Viewer • Updated May 30, 2024 • 1.42k • 37 • 5

2A2I/Aya-SambaLingo.Arabic.Chat-DPO

Viewer • Updated May 25, 2024 • 14.2k • 40 • 3

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1706887192

Viewer • Updated Feb 2, 2024 • 405 • 32

ShenaoZhang/0.0_4iters_bs256_nodpo_only4w_dataset

Viewer • Updated Apr 28, 2024 • 24k • 29

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_3_mini_0

Viewer • Updated May 5, 2024 • 5.08k • 30

arcee-ai/general-dpo-datasets

Viewer • Updated Jul 4, 2024 • 91.6k • 51

argilla/ultrafeedback-multi-binarized-preferences-cleaned

Viewer • Updated Dec 11, 2023 • 158k • 115 • 6

Asap7772/ultrafeedback_binarized_relabelled_ultrarm

Viewer • Updated Jan 24, 2024 • 63.1k • 35

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_3_mini_1

Viewer • Updated May 5, 2024 • 5.28k • 30

ibivibiv/cleaned_math_dpo_pairs

Viewer • Updated May 19, 2024 • 760k • 29

wenzhy7/llama2_orpo_ei

Viewer • Updated Jun 23, 2024 • 2.05k • 29

orpo-explorers/ultrafeedback_binarized_15k

Viewer • Updated Apr 18, 2024 • 15.4k • 30 • 4

ThWu/dpo_highest_n_random

Viewer • Updated Jul 1, 2024 • 182k • 39 • 2

agicorp/MetaMath_DPO_FewShot

Viewer • Updated Mar 23, 2024 • 395k • 37 • 2

2A2I/Aya-AceGPT.13B.Chat-DPO

Viewer • Updated May 16, 2024 • 13k • 44 • 2

Trelis/orpo-dpo-mix-40k-SHORT

Viewer • Updated May 11, 2024 • 7.19k • 41 • 2

Code-Refinement/utf_20_refs_pairs

Viewer • Updated Feb 16, 2024 • 3.68k • 31

ShenaoZ/0.0_dataup_4iters_dataset

Viewer • Updated Apr 6, 2024 • 51.8k • 30

lightblue/mitsu_top75_borda

Viewer • Updated May 30, 2024 • 2.02k • 49

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_3_mini_2

Viewer • Updated May 5, 2024 • 5.08k • 28

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_3_mini_3

Viewer • Updated May 5, 2024 • 5.09k • 30

ShenaoZ/0.00001_withdpo_4iters_bs256_555lr_dataset

Viewer • Updated May 6, 2024 • 51.8k • 27

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part1

Viewer • Updated May 6, 2024 • 19.6k • 29

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part2

Viewer • Updated May 6, 2024 • 20.7k • 29

nhyha/ORPO-DPO

Viewer • Updated Jun 12, 2024 • 1.68k • 33

cmcmaster/clinical_cases_preferences

Viewer • Updated Jun 21, 2024 • 7.94k • 31

valerielucro/gsm8k_preference_dataset_2.1

Viewer • Updated Jun 27, 2024 • 1.21k • 29

malhajar/orca_dpo_pairs-tr

Viewer • Updated Mar 30, 2024 • 10.8k • 55 • 6

Deojoandco/reward_model_anthropic

Viewer • Updated Mar 24, 2023 • 169k • 32

Astris/Nectar-Ranked-DPO

Viewer • Updated Jul 1, 2024 • 503k • 41

ShenaoZ/0.001_ablation_5iters_bs256_dataset

Viewer • Updated Apr 22, 2024 • 56.9k • 38

ShenaoZ/0.0001_withdpo_4iters_bs256_4444lr_dataset

Viewer • Updated May 5, 2024 • 51.8k • 28

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part0

Viewer • Updated May 6, 2024 • 19.6k • 29

ShenaoZ/0.0001_sft_nodpo_3iters_bs256_531lr_dataset

Viewer • Updated May 7, 2024 • 67.1k • 33

2A2I/NoRobots-Command.R-DPO

Viewer • Updated May 29, 2024 • 9.5k • 41

Tachi67/mnlp_dpo_data_7k

Viewer • Updated May 31, 2024 • 7.66k • 31

d-llm/hh-rlhf

Viewer • Updated Jun 11, 2024 • 160k • 34

allenai/coconot

Viewer • Updated Jul 18, 2024 • 13.8k • 169 • 6

vicgalle/configurable-system-prompt-multitask

Viewer • Updated Apr 23, 2024 • 1.95k • 160 • 20

reciprocate/math_dpo_pairs

Viewer • Updated Jan 5, 2024 • 4.38k • 37 • 5

vicgalle/OpenHermesPreferences-roleplay

Viewer • Updated Feb 29, 2024 • 3.06k • 44 • 6

orpo-explorers/OpenHermesPreferences-500k

Viewer • Updated Mar 30, 2024 • 500k • 30 • 2

d0rj/full-hh-rlhf-ru

Viewer • Updated Jul 2, 2024 • 125k • 51 • 2

ummagumm-a/cup-it-ds-classification-pairwise

Viewer • Updated Mar 19, 2023 • 282k • 30

ShenaoZ/0.001_ablation_4iters_bs256_decalpha_dataset

Viewer • Updated Apr 23, 2024 • 51.8k • 34

ShenaoZ/0.001_3iters_bs128_declr_nodpo_zephyrbeta_userresponse_dataset

Viewer • Updated Apr 26, 2024 • 67.1k • 30

ShenaoZ/0.001_ablation_4iters_bs256_only2third_dataset

Viewer • Updated Apr 26, 2024 • 2k • 32

YYYYYYibo/ultrafeedback_binarized_phase_2_part_1minipart_2

Viewer • Updated Apr 28, 2024 • 1k • 31

ShenaoZ/0.00005_withdpo_4iters_bs256_555lr_dataset

Viewer • Updated May 5, 2024 • 51.8k • 40

ibivibiv/nectar_dpo_cleaned

Viewer • Updated May 19, 2024 • 3.84M • 130

ibivibiv/cleaned_math_dpo_pairs_eval

Viewer • Updated May 19, 2024 • 40k • 29

mnlp-nsoai/dpo-student-preference-pairs

Viewer • Updated May 22, 2024 • 18.4k • 29

arham6/dataset2

Viewer • Updated Jun 24, 2024 • 258 • 32

aklein4/tldr-feedback-shuffled

Viewer • Updated Jun 30, 2024 • 179k • 31

fblgit/simple-math-DPO

Viewer • Updated Aug 1, 2024 • 800k • 87 • 16

abacusai/HellaSwag_DPO_FewShot

Viewer • Updated Feb 26, 2024 • 150k • 60 • 8

lamhieu/beyond_dpo_vi

Viewer • Updated Jul 1, 2024 • 25k • 47

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1707245027

Viewer • Updated Feb 7, 2024 • 1M • 33

0-hero/distilabel-math-preference-dpo

Viewer • Updated Jul 2, 2024 • 2.42k • 33

ShenaoZhang/0.001_idpo_ref_response

Viewer • Updated Apr 5, 2024 • 44.8k • 33

ShenaoZhang/0.001_idpo_same_replacechosen_only_dataset

Viewer • Updated Apr 6, 2024 • 44.8k • 34

when2rl/prm_dpo_pairs_cleaned_reformatted

Viewer • Updated Apr 19, 2024 • 7.99k • 30

thesven/pihkal-tihkal-orpo-dpo-dataset

Viewer • Updated Apr 26, 2024 • 3.46k • 33

cornfieldrm/prm800k-phase2

Viewer • Updated Apr 28, 2024 • 81.6k • 30

ShenaoZ/0.00001_withdpo_4iters_bs256_531lr_dataset

Viewer • Updated May 1, 2024 • 51.8k • 33

GENIAC-Team-Ozaki/tuninig-dataset_pref_20pct_lora-sft-finetuned-stage4-iter86000

Viewer • Updated May 22, 2024 • 20.8k • 29

2A2I/NoRobots-Aya.23.8B-DPO

Viewer • Updated May 29, 2024 • 9.5k • 43

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_2

Viewer • Updated Jun 17, 2024 • 20k • 32

mlabonne/arena-preferences

Viewer • Updated Apr 27, 2024 • 2.69k • 49 • 9

d0rj/rlhf-reward-datasets-ru

Viewer • Updated Jul 2, 2024 • 81.4k • 102 • 4

2A2I/Aya-Aya.23.8B-DPO

Viewer • Updated May 29, 2024 • 14k • 41 • 2

d0rj/synthetic-instruct-gptj-pairwise-ru

Viewer • Updated Jul 2, 2024 • 33.1k • 57 • 1

reciprocate/ultrafeedback_orca_math_cleaned_high_dpo

Viewer • Updated Jan 11, 2024 • 48.3k • 30 • 1

lamhieu/itorca_dpo_vi

Viewer • Updated Jul 1, 2024 • 12.9k • 53

SUSTech/bagel-sft

Viewer • Updated Jan 27, 2024 • 727k • 54

elfonthefly/STEM_DPO

Viewer • Updated May 23, 2024 • 1.45M • 32 • 1

YYYYYYibo/ultrafeedback_binarized_ave_pi_minpi_part_3

Viewer • Updated Jun 17, 2024 • 21.1k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_2

Viewer • Updated Jun 17, 2024 • 20k • 30

quyanh/lexglue-cot-dpo

Viewer • Updated Jul 11, 2024 • 4k • 35

efederici/alpaca-vs-alpaca-orpo-dpo

Viewer • Updated May 15, 2024 • 49.2k • 102 • 7

pszemraj/SHP-2-dpo-100k_sample

Viewer • Updated Jul 1, 2024 • 200k • 68 • 1

floleuerer/distilabel-intel-orca-dpo-pairs-binarized

Viewer • Updated Jan 14, 2024 • 5.92k • 35

arcee-ai/OpenHermesPreferences-binarized

Viewer • Updated May 18, 2024 • 989k • 63 • 1

YYYYYYibo/full_simple_online_vllm_part_2

Viewer • Updated Jul 4, 2024 • 19k • 32

YYYYYYibo/full_simple_online_vllm_part_3

Viewer • Updated Jul 4, 2024 • 19.3k • 29

YYYYYYibo/gshf_vllm_1_part_3

Viewer • Updated Jul 5, 2024 • 21.1k • 30

YYYYYYibo/gshf_train_part_3

Viewer • Updated Jul 5, 2024 • 21.1k • 31

BramVanroy/orca_dpo_pairs_dutch

Viewer • Updated 29 days ago • 11k • 59 • 5

erhwenkuo/rlhf_reward_single_round-chinese-zhtw

Viewer • Updated Oct 4, 2023 • 24.9k • 45 • 3

HuggingFaceH4/cai-conversation

Viewer • Updated Dec 6, 2023 • 169k • 36 • 4

We-Want-GPU/yi-ko-DPO-noprompt-dataset

Viewer • Updated Dec 6, 2023 • 3.83k • 30 • 2

allenai/reward-bench-results

Updated 23 days ago • 9.14k • 2

droussis/UltraSafety_binarized-orpo-dpo

Viewer • Updated Apr 25, 2024 • 2.26k • 36 • 2

AlexHung29629/stack-exchange-paired-128K

Viewer • Updated Jul 3, 2024 • 128k • 31 • 1

giux78/50000-60900-ultrafeedback-binarized-preferences-cleaned-ita

Viewer • Updated Jan 17, 2024 • 10.9k • 30

roleplay4fun/chai-valid-pairs-ss5-v1.0

Viewer • Updated Feb 27, 2024 • 12.2k • 30

orpo-explorers/OpenHermesPreferences-50k

Viewer • Updated Mar 30, 2024 • 50k • 28

Tachi67/mnlp_dpo_data

Viewer • Updated May 24, 2024 • 25.4k • 28

euiyulsong/sci_train_ds

Viewer • Updated May 14, 2024 • 11.7k • 29

arcee-ai/truthy-dpo-v0.1-binarized

Viewer • Updated May 18, 2024 • 1.02k • 39

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_1_mini_3

Viewer • Updated May 19, 2024 • 5k • 30

2A2I/NoRobots-SambaLingo.Arabic.Chat-DPO

Viewer • Updated May 29, 2024 • 9.5k • 33

patruff/chuckles_dpo_pairsA

Viewer • Updated May 27, 2024 • 106 • 36

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_2_mini_0

Viewer • Updated Jun 17, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_minpi_part_2

Viewer • Updated Jun 17, 2024 • 20k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_3

Viewer • Updated Jun 18, 2024 • 21.1k • 32

varun-v-rao/mimic_cxr_dpo

Viewer • Updated Dec 10, 2023 • 125k • 60

alvarobartt/ultrafeedback-multi-binarized-quality-preferences-cleaned

Viewer • Updated Dec 20, 2023 • 155k • 31

Sharathhebbar24/orca_dpo_pairs

Viewer • Updated Feb 10, 2024 • 12.9k • 34

jikaixuan/mistral02_generated

Viewer • Updated Feb 27, 2024 • 61.1k • 38

quirky-lats-at-mats/NORMAL_BACKDOOR_alpaca_sleeper_agents_toy_safety_NOT_TRUNCATED_v4

Viewer • Updated Mar 11, 2024 • 2.83k • 28

ShenaoZ/0.0_dataup_dataset

Viewer • Updated Apr 5, 2024 • 44.8k • 30

YYYYYYibo/eval-dataset-nash

Viewer • Updated May 2, 2024 • 1k • 31

ShenaoZ/0.0005_withdpo_4iters_bs256_555lr_dataset

Viewer • Updated May 5, 2024 • 51.8k • 30

ShenaoZhang/0.0_zephyr_5551_4iters_bs256_dataset

Viewer • Updated May 13, 2024 • 2k • 34

euiyulsong/generated_data

Viewer • Updated May 17, 2024 • 452 • 29

arcee-ai/OpenHermes2.5-dpo-binarized-alpha

Viewer • Updated May 18, 2024 • 9.79k • 44

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_3

Viewer • Updated May 20, 2024 • 21.1k • 30

2A2I/NoRobots-AceGPT.13B.Chat-DPO

Viewer • Updated May 29, 2024 • 9.5k • 31

jayhii/orpo_2sep_data_font

Viewer • Updated Jun 7, 2024 • 10k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_2_mini_3

Viewer • Updated Jun 16, 2024 • 5k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_2_mini_0

Viewer • Updated Jun 16, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_2_mini_1

Viewer • Updated Jun 16, 2024 • 5k • 32

YYYYYYibo/ultrafeedback_binarized_ave_pi_minpi_part_2

Viewer • Updated Jun 17, 2024 • 20k • 29

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_3

Viewer • Updated Jun 17, 2024 • 21.1k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_2_mini_0

Viewer • Updated Jun 17, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_minpi_part_3

Viewer • Updated Jun 18, 2024 • 21.1k • 32

valerielucro/gsm8k_preference_dataset_2

Viewer • Updated Jun 27, 2024 • 379 • 32

reshinthadith/pairwise-code-review-instruct-critique-revision-python

Viewer • Updated Jan 9, 2023 • 5.24k • 48 • 9

NickyNicky/neovalle_H4rmony_dpo_translated_English_to_Spanish

Viewer • Updated May 17, 2024 • 2.02k • 36 • 4

HuggingFaceH4/cai-conversation-harmless-old

Viewer • Updated Dec 10, 2023 • 44.8k • 57 • 3

Starlento/DPO-En-Zh-20k-handbook

Viewer • Updated May 2, 2024 • 20k • 38 • 3

AlekseyKorshuk/davinci-pairwise-medium

Viewer • Updated Feb 8, 2023 • 72k • 44

AlekseyKorshuk/cup-it-ds-pairwise

Viewer • Updated Mar 18, 2023 • 352k • 31

banghua/hh_reward_model_labeled

Viewer • Updated Aug 6, 2023 • 125k • 45

pvduy/dpo_data

Viewer • Updated Jan 11, 2024 • 197k • 33

vwxyzjn/cai-conversation-dev1705951688

Viewer • Updated Jan 22, 2024 • 256 • 40

lamhieu/beyond_dpo_en

Viewer • Updated Jul 1, 2024 • 25k • 53

CognitiveLab/hh-rlhf-json

Viewer • Updated Jan 24, 2024 • 161k • 29

vwxyzjn/openhermes-dev__mistralai_Mistral-7B-Instruct-v0.1__1707330973

Viewer • Updated Feb 7, 2024 • 167 • 35

sanduntg/test_vsort_classification

Viewer • Updated Feb 8, 2024 • 99 • 37

vwxyzjn/ultrafeedback_binarized_1707921333

Viewer • Updated Feb 14, 2024 • 2k • 43

mnoukhov/openai_comparisons_20k_regen_and_relabelled

Viewer • Updated Feb 18, 2024 • 20k • 32

vwxyzjn/ultrafeedback_binarized_1708454270

Viewer • Updated Feb 20, 2024 • 25.3k • 41

vwxyzjn/ultrafeedback_binarized_1708458397

Viewer • Updated Feb 20, 2024 • 25.3k • 34

Baidicoot/anthropic_hh_golden_mistral

Viewer • Updated Mar 1, 2024 • 42.1k • 30

hon9kon9ize/yue-truthy

Viewer • Updated Mar 8, 2024 • 2.03k • 40

vwxyzjn/hh-rlhf

Viewer • Updated Mar 13, 2024 • 100 • 35

reciprocate/dpo_ultra-capybara_filtered-best

Viewer • Updated Mar 14, 2024 • 25.6k • 29

UCLAML/data-RPO-Iter1-New-309_generated

Viewer • Updated Apr 21, 2024 • 20k • 36

ShenaoZ/0.001_ablation_4iters_bs256_nodpo_dataset

Viewer • Updated Apr 23, 2024 • 69.1k • 39

ShenaoZ/0.001_ablation_4iters_bs256_useresponse_dataset

Viewer • Updated Apr 26, 2024 • 17.3k • 29

ShenaoZhang/0.0001_3iters_bs256_nodpo_full6w_dataset

Viewer • Updated Apr 29, 2024 • 67.1k • 37

YYYYYYibo/ultrafeedback_binarized_phase_2_ranked

Viewer • Updated Apr 29, 2024 • 9.28k • 30

nbalepur/Mnemonic_Chosen_Rejected

Viewer • Updated Apr 29, 2024 • 472 • 31

YYYYYYibo/eval-dataset-with-score-rank4

Viewer • Updated May 2, 2024 • 200 • 30

ShenaoZ/0.0001_withdpo_3iters_bs256_531lr_dataset

Viewer • Updated May 3, 2024 • 44.8k • 30

vipinkatara/dataset_complete_12

Viewer • Updated May 3, 2024 • 220k • 31

YYYYYYibo/ultrafeedback_binarized_epoch_2_minpi_part_1

Viewer • Updated May 3, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_epoch_2_vllm_part_2

Viewer • Updated May 3, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_epoch_2_minpi_part_3

Viewer • Updated May 4, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_rank4_all_train_part_3

Viewer • Updated May 5, 2024 • 20.5k • 30

StrangeSX/SGXT1

Viewer • Updated May 5, 2024 • 99 • 39

YYYYYYibo/ultrafeedback_binarized_dataset_offline_part1

Viewer • Updated May 6, 2024 • 19.6k • 32

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_minpi_part_2

Viewer • Updated May 7, 2024 • 19.1k • 28

ShenaoZ/0.0001_sft_nodpo_5iters_bs256_5102lr_dataset

Viewer • Updated May 8, 2024 • 71.1k • 33

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_3

Viewer • Updated May 9, 2024 • 4.85k • 28

YYYYYYibo/ultrafeedback_binarized_rank4_on_vanilla_part_3

Viewer • Updated May 16, 2024 • 21.1k • 30

DuongTrongChi/detoxic-dpo-format

Viewer • Updated May 16, 2024 • 46.6k • 29

arcee-ai/multiturn-capybara-preferences-filtered-binarized

Viewer • Updated May 18, 2024 • 14.8k • 38

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.20

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.00

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.00

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.00

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.50

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.50

Updated May 20, 2024 • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_2_mini_1

Viewer • Updated May 20, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_2_mini_2

Viewer • Updated May 20, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_3_mini_0

Viewer • Updated May 20, 2024 • 5.28k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_3

Viewer • Updated May 20, 2024 • 21.1k • 32

mcding-org/CorrectDPO-Eval-DPO_Pm3B_U0_beta0.10

Updated May 21, 2024 • 32

mcding-org/CorrectDPO-Eval-DPO_L8B_U0_beta0.10

Updated May 21, 2024 • 30

Piteryo/hf-trl-1024

Viewer • Updated May 24, 2024 • 1.28k • 33

ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized

Viewer • Updated Jun 12, 2024 • 60.9k • 42

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_2_mini_2

Viewer • Updated Jun 16, 2024 • 5k • 28

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_2_mini_3

Viewer • Updated Jun 17, 2024 • 5k • 32

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_3_mini_2

Viewer • Updated Jun 17, 2024 • 5.28k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_3_mini_3

Viewer • Updated Jun 17, 2024 • 5.29k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_2_mini_0

Viewer • Updated Jun 17, 2024 • 5k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_3_mini_3

Viewer • Updated Jun 17, 2024 • 5.29k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_3_mini_3

Viewer • Updated Jun 18, 2024 • 5.29k • 33

y1xing/orpo_llama3_concatenated_data_with_chris_examples_orpo_instruct_dataset

Viewer • Updated Jul 6, 2024 • 2.64k • 33

argilla/ultrafeedback-multi-binarized-quality-preferences-cleaned

Viewer • Updated Dec 11, 2023 • 155k • 41 • 4

mii-community/ultrafeedback-preferences-translated-ita

Viewer • Updated Feb 21, 2024 • 60.9k • 39 • 3

vicgalle/OpenHermesPreferences-1k

Viewer • Updated Feb 29, 2024 • 1.11k • 32 • 3

mlabonne/oasst-preferences

Viewer • Updated Apr 22, 2024 • 22.3k • 49 • 3

beyond/rlhf-reward-single-round

Viewer • Updated Jul 4, 2023 • 25k • 41 • 2

alvarobartt/Anthropic_HH_Golden_Formatted

Viewer • Updated Dec 14, 2023 • 44.8k • 30 • 2

distilabel-internal-testing/ohp-writing

Viewer • Updated Apr 10, 2024 • 1.53k • 34 • 2

NickyNicky/function_call_orpo_sft_phi3_chatML_only

Viewer • Updated May 2, 2024 • 66k • 51 • 2

PawanKrd/dpo-gpt-4o

Viewer • Updated Jun 28, 2024 • 12.4k • 77 • 14

d0rj/oasst1_pairwise_rlhf_reward-ru

Viewer • Updated Jul 2, 2024 • 18.9k • 36 • 1

Palash123/dpo_anthropic_hh_rlhf

Viewer • Updated Dec 4, 2023 • 168k • 39 • 1

sablo/HelpSteer_binarized

Viewer • Updated Jan 18, 2024 • 8.55k • 48 • 1

SUSTech/bagel-dpo

Viewer • Updated Jan 27, 2024 • 192k • 30 • 1

winglian/cortex-0_1-loss

Viewer • Updated Feb 10, 2024 • 402 • 54 • 1

vtiyyal1/AskDocsEmpathy_4k_dpo

Viewer • Updated Mar 11, 2024 • 4.12k • 28 • 1

Suraponn/iapp_for_orpo

Viewer • Updated Mar 18, 2024 • 121k • 31 • 1

umarigan/openhermespreference_tr

Viewer • Updated Apr 24, 2024 • 989k • 35 • 3

orpo-explorers/OHP-15k

Viewer • Updated Apr 22, 2024 • 15.4k • 33 • 1

NickyNicky/oasst2_orpo_mix_tokenizer_phi_3_v1

Viewer • Updated Apr 30, 2024 • 54.3k • 35 • 1

NickyNicky/Colossal_Translation_EN_ES_ORPO_DPO_Gemma

Viewer • Updated May 6, 2024 • 1.7M • 36 • 2

NickyNicky/DIBT_prompts_ranked_En_Es_orpo_dpo_chatML_gemma_V3

Viewer • Updated May 14, 2024 • 20.4k • 33 • 1

NickyNicky/nano_finance_200k_en_es_chatML_gemma_orpo_dpo

Viewer • Updated May 29, 2024 • 201k • 40 • 1

AlekseyKorshuk/chai-real-and-synthetic

Viewer • Updated Feb 10, 2023 • 154k • 46

ummagumm-a/cup-it-ds-classification-pairwise-train-val

Viewer • Updated Mar 19, 2023 • 352k • 31

AlekseyKorshuk/lmeh-hh

Viewer • Updated May 18, 2023 • 12.5k • 31

samxm111/rlhf-reward-single-round

Viewer • Updated Aug 19, 2023 • 25k • 31

abhishek/dpo-sample

Viewer • Updated Oct 30, 2023 • 7 • 33

alvarobartt/Anthropic_HH_Golden_Extended

Viewer • Updated Dec 14, 2023 • 89.7k • 37

mnoukhov/openai_summarize_generated_20k_relabel_410m_dpo1

Viewer • Updated Dec 18, 2023 • 20k • 32

mnoukhov/openai_summarize_generated_20k_relabel_1b

Viewer • Updated Dec 18, 2023 • 20k • 31

dvilasuero/multiturn_with_generations

Viewer • Updated Dec 20, 2023 • 100 • 33

GokhanAI/INST_Synthetic_LLAMA

Viewer • Updated Dec 22, 2023 • 26.3k • 44

0x7o/oasst-ru-dpo-v1

Viewer • Updated Dec 27, 2023 • 1.32k • 34

Jaredquek/dpoedtech

Viewer • Updated Jan 5, 2024 • 3.25k • 29

jan-hq/ultrafeedback_quality_binarized

Viewer • Updated Jan 9, 2024 • 155k • 40

giux78/10000-20000-ultrafeedback-binarized-preferences-cleaned-ita

Viewer • Updated Jan 16, 2024 • 10k • 30

giux78/20000-50000-ultrafeedback-binarized-preferences-cleaned-ita

Viewer • Updated Jan 17, 2024 • 30k • 32

vwxyzjn/cai-conversation-dev1705525723

Viewer • Updated Jan 17, 2024 • 256 • 28

CognitiveLab/hh-rlhf-formatted

Viewer • Updated Jan 18, 2024 • 161k • 30

CognitiveLab/hh-rlhf-formatted-10000

Viewer • Updated Jan 18, 2024 • 10k • 29

vwxyzjn/cai-conversation-dev1705633234

Viewer • Updated Jan 19, 2024 • 256 • 38

arianhosseini/openai_comparisons_20k_regen_and_relabelled

Viewer • Updated Jan 21, 2024 • 25k • 28

Saugatkafley/okapi-ranking

Viewer • Updated Jul 2, 2024 • 126k • 40

vwxyzjn/self-reward-dev1706043619

Viewer • Updated Jan 23, 2024 • 16 • 50

vwxyzjn/self-reward-dev1706109551

Viewer • Updated Jan 24, 2024 • 16 • 33

vwxyzjn/self-reward-dev1706112590

Viewer • Updated Jan 24, 2024 • 16 • 49

manishiitg/unalignment-toxic-dpo-v0.2

Viewer • Updated Jan 29, 2024 • 1.08k • 40

manishiitg/jondurbin-gutenberg-dpo-v0.1

Viewer • Updated Jan 29, 2024 • 1.8k • 37

argilla/ultrafeedback-capybara-mix-5k

Viewer • Updated Jan 29, 2024 • 5k • 30

BarraHome/ultrafeedback_binarized

Viewer • Updated Jan 31, 2024 • 187k • 125

remyxai/ffmperative_dpo_test

Viewer • Updated Feb 2, 2024 • 1.47k • 46

vwxyzjn/openhermes-dev__mistralai_Mistral-7B-Instruct-v0.1__1706885434

Viewer • Updated Feb 2, 2024 • 24 • 30

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1706903049

Viewer • Updated Feb 2, 2024 • 167 • 28

weijie210/UFB_prefs_iter_0

Viewer • Updated Feb 3, 2024 • 24.9k • 30

weijie210/UFB_prefs_nosub_iter_0

Viewer • Updated Feb 6, 2024 • 14.7k • 30

pvduy/dpo_data_capy

Viewer • Updated Feb 3, 2024 • 47.6k • 36

dkshjn/processed_distilabel-capybara-dpo-7k-binarized

Viewer • Updated Feb 4, 2024 • 7.56k • 28

weijie210/UC_prefs_nosub_iter_0

Viewer • Updated Feb 5, 2024 • 14.4k • 35

weijie210/UC_prefs_iter_0_pairwise

Viewer • Updated Feb 5, 2024 • 14.4k • 28

vwxyzjn/openhermes-dev__mistralai_Mistral-7B-Instruct-v0.1__1707331096

Viewer • Updated Feb 7, 2024 • 87 • 35

vwxyzjn/openhermes-dev__mistralai_Mistral-7B-Instruct-v0.1__1707331527

Viewer • Updated Feb 7, 2024 • 462 • 37

vwxyzjn/openhermes-dev__meta-llama_Llama-2-70b-chat-hf__1707332943

Viewer • Updated Feb 7, 2024 • 167 • 36

nz/100_v2_rlhf

Viewer • Updated Feb 12, 2024 • 122k • 32

vwxyzjn/ultrafeedback_binarized_1708035667

Viewer • Updated Feb 15, 2024 • 63.1k • 33

zekeZZ/hh-rlhf-dpo

Viewer • Updated Feb 17, 2024 • 51.9k • 39

vwxyzjn/ultrafeedback_binarized_1708702930

Viewer • Updated Feb 23, 2024 • 27k • 37

jikaixuan/mistral_generated

Viewer • Updated Feb 27, 2024 • 61.1k • 29

arianhosseini/summ_dpo1b1_ngen10_max_2ndmax

Viewer • Updated Mar 10, 2024 • 20k • 32

nz/closest_to_3000_range_1000_to_9000

Viewer • Updated Mar 2, 2024 • 11k • 39

nz/closest_to_5000_range_1000_to_9000

Viewer • Updated Mar 2, 2024 • 11k • 34

nz/closest_to_7000_range_1000_to_9000

Viewer • Updated Mar 3, 2024 • 11k • 32

hon9kon9ize/yue-toxic-dpo

Viewer • Updated Mar 14, 2024 • 1.07k • 30

David-Xu/astronomy-stack-dpo-text-20-percent

Viewer • Updated Mar 10, 2024 • 3.99k • 30 • 1

psyche/anthropic-hh-rlhf

Viewer • Updated Mar 11, 2024 • 169k • 90

aengusl/noise5_alpaca_sleeper_agents_toy_safety_v4

Viewer • Updated Mar 11, 2024 • 2.83k • 33

aengusl/test_hp_dpo_unlrn_ds

Viewer • Updated Mar 11, 2024 • 312 • 33

vwxyzjn/hh-rlhf-trl-style

Viewer • Updated Mar 13, 2024 • 100 • 35

valerielucro/Preference-Dataset-sample

Viewer • Updated Mar 16, 2024 • 525 • 30

abhinand/argilla-dpo-mix-7k-singleturn

Viewer • Updated Mar 18, 2024 • 4.9k • 35

nz/ulma_anthropic_hh_golden

Viewer • Updated Mar 19, 2024 • 44.8k • 32

when2rl/dpo-mix-7k-rescaled_reformatted

Viewer • Updated Apr 17, 2024 • 7.5k • 34

orpo-explorers/OpenHermesPreferences-25k

Viewer • Updated Mar 30, 2024 • 25k • 29

orpo-explorers/OpenHermesPreferences-250k

Viewer • Updated Mar 30, 2024 • 250k • 28

sazirarrwth99/kangoroo_dpo_trainer_final

Viewer • Updated Apr 1, 2024 • 23.3k • 33

wenbopan/cmmlu_dpo_pairs

Viewer • Updated Apr 3, 2024 • 5.04k • 36

ShenaoZhang/0.001_idpo_dataset

Viewer • Updated Apr 5, 2024 • 44.8k • 31

Gopal2002/zephyr-gemma-finetune-dpo

Viewer • Updated Apr 6, 2024 • 69 • 31

AnushaKulkarni/preferred_dataset2

Viewer • Updated Apr 7, 2024 • 50 • 30

mnoukhov/summarize_from_feedback_tldr3_generated_20k_vllm_pythia1b_dpo_temp0.7

Viewer • Updated Apr 7, 2024 • 20k • 40

arianhosseini/ultrafeedback_binarized_relabel1b

Viewer • Updated Apr 8, 2024 • 63.1k • 31

ShenaoZ/0.0001_idpo_same_6iters_dataset

Viewer • Updated Apr 13, 2024 • 48.8k • 31

ShenaoZ/0.001_idpo_same_scratch_dataset

Viewer • Updated Apr 14, 2024 • 106k • 27

mnoukhov/summarize_from_feedback_tldr3_generated_20k_relabel_pythia1b_dpo_temp0.7_length128

Viewer • Updated Apr 14, 2024 • 20k • 33

ShenaoZ/0.0001_idpo_same_3itersn_dataset

Viewer • Updated Apr 14, 2024 • 44.8k • 30

trl-lib/capybara-preferencces-7k

Viewer • Updated Apr 15, 2024 • 7.56k • 37

guoyu-zhang/usp_1

Viewer • Updated Apr 15, 2024 • 1k • 31

guoyu-zhang/usp_2

Viewer • Updated Apr 15, 2024 • 1k • 31

guoyu-zhang/usp_4

Viewer • Updated Apr 15, 2024 • 1k • 30

DuongTrongChi/hh-rlhf

Viewer • Updated Apr 16, 2024 • 161k • 29

when2rl/gutenberg-dpo-v0.1_reformatted

Viewer • Updated Apr 17, 2024 • 918 • 29

ShenaoZ/0.001_ablation_dataset

Viewer • Updated Apr 18, 2024 • 44.8k • 33

ShenaoZ/0.0001_ablation_dataset

Viewer • Updated Apr 18, 2024 • 44.8k • 31

mnoukhov/summarize_from_feedback_tldr3_labelled_vllm_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 19, 2024 • 9.5k • 31

ShenaoZ/0.0001_ablation_4iters_bs256_dataset

Viewer • Updated Apr 22, 2024 • 51.8k • 32

ShenaoZ/0.01_ablation_4iters_bs256_dataset

Viewer • Updated Apr 23, 2024 • 51.8k • 27

UCLAML/RPO-Iter2-New-312_generated

Viewer • Updated Apr 23, 2024 • 20k • 46

orpo-explorers/OHP-15k-Stratified-1

Viewer • Updated Apr 23, 2024 • 15k • 32

orpo-explorers/OHP-15k-Stratified-2

Viewer • Updated Apr 23, 2024 • 15k • 28

orpo-explorers/OHP-15k-Stratified-3

Viewer • Updated Apr 23, 2024 • 15k • 33

distilabel-internal-testing/ultrafeedback-mini-dpo

Viewer • Updated Apr 24, 2024 • 10 • 29

ShenaoZhang/0.001_ablation_5iters_bs128_dataset

Viewer • Updated Apr 25, 2024 • 12.2k • 31

ShenaoZ/0.001_3iters_bs128_declr_nodpo_useresponse_dataset

Viewer • Updated Apr 26, 2024 • 67.1k • 33

ShenaoZ/0.001_4iters_bs128_declr_nodpo_useresponse_dataset

Viewer • Updated Apr 26, 2024 • 69.1k • 28

ShenaoZ/0.001_3iters_bs256_declr_nodpo_userresponse_dataset

Viewer • Updated Apr 26, 2024 • 67.1k • 37

NickyNicky/mlabonne_orpo-dpo-mix-40k

Viewer • Updated Apr 26, 2024 • 44.2k • 29

theGhoul21/dpo-dataset

Viewer • Updated Apr 28, 2024 • 4.82k • 32

ShenaoZ/0.001_4iters_bs256_nodpo_only2third_dataset

Viewer • Updated Apr 26, 2024 • 12.2k • 29

ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_dataset

Viewer • Updated Apr 27, 2024 • 48k • 36

ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_dataset

Viewer • Updated Apr 27, 2024 • 48k • 33

ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_zephyr_dataset

Viewer • Updated Apr 27, 2024 • 48k • 40

ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_dataset

Viewer • Updated Apr 27, 2024 • 48k • 29

ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_dataset

Viewer • Updated Apr 27, 2024 • 48k • 32

YYYYYYibo/ultrafeedback_binarized_phase_1_part_1_ranked

Viewer • Updated Apr 27, 2024 • 10k • 29

ShenaoZhang/0.0001_4iters_bs256_nodpo_only4w_dataset

Viewer • Updated Apr 28, 2024 • 62k • 34

YYYYYYibo/ultrafeedback_binarized_phase_2_part_2

Viewer • Updated Apr 28, 2024 • 5.28k • 30

YYYYYYibo/ultrafeedback_binarized_phase_2_part_1minipart_0

Viewer • Updated Apr 28, 2024 • 1k • 30

YYYYYYibo/ultrafeedback_binarized_phase_2_part_1minipart_3

Viewer • Updated Apr 28, 2024 • 1k • 31

communityai/system_identity_remove_preference_openai

Viewer • Updated Apr 28, 2024 • 93 • 29

communityai/system_identity_remove_preference_microsoft

Viewer • Updated Apr 28, 2024 • 93 • 33

theGhoul21/dpo-dataset-v2

Viewer • Updated Apr 29, 2024 • 4.83k • 32

ShenaoZhang/0.0001_3iters_bs256_nodpo_full6w_userresponse_dataset

Viewer • Updated Apr 29, 2024 • 46.8k • 32

YYYYYYibo/ultrafeedback_binarized_left_part_2

Viewer • Updated May 1, 2024 • 15k • 30

nnheui/stablelm-2-1_6b-sft-full-ultrafeedback_generated

Viewer • Updated Apr 30, 2024 • 61.1k • 31 • 1

YYYYYYibo/ultrafeedback_binarized_vllm_part_3

Viewer • Updated May 1, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_train_part_3

Viewer • Updated May 2, 2024 • 26.1k • 37

when2rl/mt_bench_human_judgments_reformatted

Viewer • Updated May 2, 2024 • 8.96k • 30

ShenaoZ/0.0001_withdpo_4iters_bs256_511lr_dataset

Viewer • Updated May 1, 2024 • 51.8k • 28

ShenaoZ/0.0_withdpo_4iters_bs256_531lr_dataset

Viewer • Updated May 2, 2024 • 51.8k • 30

theGhoul21/irpo-dataset-v1

Viewer • Updated May 3, 2024 • 11k • 30

four-two-labs/orpo-test

Viewer • Updated May 1, 2024 • 60.9k • 30

YYYYYYibo/eval-dataset-vanilla

Viewer • Updated May 3, 2024 • 200 • 32

iamnguyen/ultrafeedback_translated

Viewer • Updated May 2, 2024 • 999 • 27

YYYYYYibo/eval-dataset-with-score-nash

Viewer • Updated May 2, 2024 • 200 • 29

YYYYYYibo/ultrafeedback_binarized_plus_vllm_part_3

Viewer • Updated May 3, 2024 • 5k • 28

ShenaoZ/0.0001_withdpo_3iters_bs256_551lr_dataset

Viewer • Updated May 3, 2024 • 44.8k • 32

vipinkatara/dataset_complete_1

Viewer • Updated May 3, 2024 • 63.1k • 29

YYYYYYibo/ultrafeedback_binarized_epoch_2_train_part_1

Viewer • Updated May 3, 2024 • 25k • 29

YYYYYYibo/ultrafeedback_binarized_epoch_2_train_part_2

Viewer • Updated May 3, 2024 • 25k • 29

ShenaoZ/0.0001_withdpo_4iters_bs256_5102lr_misit_correct_dataset

Viewer • Updated May 4, 2024 • 51.8k • 33

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_2_mini_3

Viewer • Updated May 4, 2024 • 5k • 31

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_2_mini_1

Viewer • Updated May 4, 2024 • 5k • 28

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_2_mini_0

Viewer • Updated May 4, 2024 • 4.8k • 29

ShenaoZ/0.0005_withdpo_4iters_bs256_5102lr_dataset

Viewer • Updated May 5, 2024 • 51.8k • 28

ShenaoZ/0.0001_withdpo_4iters_bs256_3333lr_dataset

Viewer • Updated May 5, 2024 • 51.8k • 35

YYYYYYibo/ultrafeedback_binarized_real_rank4_all_minpi_part_3

Viewer • Updated May 5, 2024 • 20.5k • 29

ShenaoZ/0.0001_sft_nodpo_3iters_bs256_555lr_dataset

Viewer • Updated May 6, 2024 • 67.1k • 32

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_dpo_costa_2.8b_bf16.yml_6e799_new

Viewer • Updated May 5, 2024 • 20k • 34

YYYYYYibo/ultrafeedback_binarized_new_gen_part_2

Viewer • Updated May 6, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_new_gen_part_3

Viewer • Updated May 6, 2024 • 5k • 33

YYYYYYibo/ultrafeedback_binarized_dataset_offline_part0

Viewer • Updated May 6, 2024 • 19.6k • 31

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part1_mini_3

Viewer • Updated May 6, 2024 • 4.9k • 31

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part1_mini_2

Viewer • Updated May 6, 2024 • 4.9k • 30

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part2_mini_3

Viewer • Updated May 6, 2024 • 5.19k • 30

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part2_mini_1

Viewer • Updated May 6, 2024 • 5.18k • 30

Baidicoot/helpful-harmful-rlhf

Viewer • Updated May 9, 2024 • 161k • 29

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_2_mini_2

Viewer • Updated May 7, 2024 • 4.1k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_2_mini_1

Viewer • Updated May 7, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_2_mini_0

Viewer • Updated May 7, 2024 • 4.78k • 30

ShenaoZ/0.0001_withdpo_3iters_bs256_5102lr_dataset

Viewer • Updated May 8, 2024 • 44.8k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_3_mini_3

Viewer • Updated May 8, 2024 • 5.09k • 29

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_minpi_part_3

Viewer • Updated May 8, 2024 • 20.7k • 30

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_2_mini_2

Viewer • Updated May 8, 2024 • 4.4k • 28

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_2_mini_1

Viewer • Updated May 8, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_minpi_part_2

Viewer • Updated May 8, 2024 • 19.4k • 28

ShenaoZ/0.001_withdpo_4iters_bs256_555lr_dataset

Viewer • Updated May 9, 2024 • 51.8k • 33

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_2

Viewer • Updated May 9, 2024 • 4.85k • 35

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_1

Viewer • Updated May 9, 2024 • 4.85k • 29

uine/single-dpo-practice-dataset

Viewer • Updated May 9, 2024 • 2.11k • 32

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_0

Viewer • Updated May 9, 2024 • 5.16k • 30

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_1

Viewer • Updated May 9, 2024 • 5.16k • 29

when2rl/hh-rlhf_reformatted

Viewer • Updated May 9, 2024 • 169k • 36

ShenaoZ/0.0001_withdpo_4iters_bs256_5551lr_dataset

Viewer • Updated May 10, 2024 • 51.8k • 30

ShenaoZ/0.0005_withdpo_4iters_bs256_2epoch_5311lr_dataset

Viewer • Updated May 10, 2024 • 51.8k • 36

ShenaoZ/0.0005_withdpo_4iters_bs256_2epoch_5551lr_dataset

Viewer • Updated May 10, 2024 • 51.8k • 36

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_pythia410m-dpo-tldr

Viewer • Updated May 17, 2024 • 107k • 30

ContextualAI/tiny_train_test_ultrafeedback_binarized

Viewer • Updated May 12, 2024 • 20 • 34

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_pythia410m-dpo-tldr-step873

Viewer • Updated May 12, 2024 • 20k • 40

ShenaoZhang/0.0001_zephyr_5551_4iters_bs256_dataset

Viewer • Updated May 14, 2024 • 51.8k • 48

DuongTrongChi/dpo-detoxic

Viewer • Updated May 16, 2024 • 46.6k • 27

euiyulsong/arc_easy

Viewer • Updated May 17, 2024 • 2.25k • 29

arcee-ai/ultrafeedback-binarized

Viewer • Updated May 18, 2024 • 60.9k • 30

euiyulsong/generated_data_all_cos_1000

Viewer • Updated May 18, 2024 • 1k • 29

Aditya685/dpo_data

Viewer • Updated Jul 4, 2024 • 3.15k • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_1_mini_0

Viewer • Updated May 19, 2024 • 5k • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_1_mini_2

Viewer • Updated May 19, 2024 • 5k • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.00

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.00

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.10

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.00

Updated May 20, 2024 • 28

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.20

Updated May 20, 2024 • 28

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.00

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.30

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.00

Updated May 20, 2024 • 32

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.00

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.30

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.10

Updated May 20, 2024 • 32

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.50

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.30

Updated May 20, 2024 • 27

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.10

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.10

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.20

Updated May 20, 2024 • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_1_mini_3

Viewer • Updated May 20, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_1_mini_2

Viewer • Updated May 20, 2024 • 5k • 29

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.40

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.40

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.40

Updated May 20, 2024 • 27

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.50

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.50

Updated May 20, 2024 • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_2

Viewer • Updated May 20, 2024 • 20k • 32

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_3_mini_1

Viewer • Updated May 20, 2024 • 5.28k • 29

mcding-org/CorrectDPO-Dataset-U10

Updated May 21, 2024 • 28

mcding-org/CorrectDPO-Dataset-U30

Updated May 21, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Pm3B_U0_beta0.10r0.30rho0.20

Updated May 21, 2024 • 30

GENIAC-Team-Ozaki/tuninig-dataset_pref_20pct_v2_full-sft-finetuned-stage4-iter86000-v2

Viewer • Updated May 23, 2024 • 18.8k • 30

berquetR/dpo_preference_dataset

Preview • Updated May 26, 2024 • 31

when2rl/UltraInteract_pair_reformatted_filtered

Viewer • Updated May 27, 2024 • 166k • 33

BahaaEldin0/openai_summarize_comparisons_dataset_with_prompts_2_percent

Viewer • Updated May 30, 2024 • 4.69k • 31

TTTXXX01/My-Zephyr-7B-dataset

Viewer • Updated Jun 2, 2024 • 51.8k • 35

WKLI22/orpo-dpo-mix-zh-40k

Viewer • Updated Jun 6, 2024 • 44.2k • 37

ihughes15234/tictactoe_DPO

Viewer • Updated Jun 5, 2024 • 765 • 38

nhyha/DPO_2

Viewer • Updated Jun 12, 2024 • 5 • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_2_mini_2

Viewer • Updated Jun 17, 2024 • 5k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_2_mini_1

Viewer • Updated Jun 17, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_3_mini_1

Viewer • Updated Jun 17, 2024 • 5.28k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_vllm_part_3_mini_0

Viewer • Updated Jun 17, 2024 • 5.28k • 32

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_3_mini_0

Viewer • Updated Jun 17, 2024 • 5.28k • 29

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_3_mini_1

Viewer • Updated Jun 17, 2024 • 5.28k • 34

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_3_mini_2

Viewer • Updated Jun 17, 2024 • 5.28k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_train_part_3_mini_3

Viewer • Updated Jun 17, 2024 • 5.29k • 31

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_2_mini_2

Viewer • Updated Jun 17, 2024 • 5k • 28

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_2_mini_1

Viewer • Updated Jun 17, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_2_mini_3

Viewer • Updated Jun 17, 2024 • 5k • 28

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_2_mini_2

Viewer • Updated Jun 17, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_3_mini_0

Viewer • Updated Jun 17, 2024 • 5.28k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_3_mini_2

Viewer • Updated Jun 17, 2024 • 5.28k • 32

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_3_mini_0

Viewer • Updated Jun 18, 2024 • 5.28k • 29

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_3_mini_1

Viewer • Updated Jun 18, 2024 • 5.28k • 29

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_3_mini_2

Viewer • Updated Jun 18, 2024 • 5.28k • 27

mnoukhov/summarize_from_feedback_oai_preprocessing_1706381144_relabel2_llama8b

Viewer • Updated Jun 19, 2024 • 92.1k • 34

Dahoas/static-hh

Viewer • Updated Mar 6, 2023 • 101k • 66 • 20

davanstrien/dataset-tldr-preference-dpo

Viewer • Updated Apr 30, 2024 • 522 • 48 • 11

declare-lab/audio-alpaca

Viewer • Updated Jul 18, 2024 • 15k • 82 • 14

ThWu/dpo_openhermes

Viewer • Updated Jul 1, 2024 • 183k • 33 • 6

HuggingFaceH4/grok-conversation-harmless2

Viewer • Updated Jan 19, 2024 • 44.8k • 48 • 7

monology/oasst2_dpo

Viewer • Updated Dec 24, 2023 • 28.4k • 40 • 3

HuggingFaceH4/orca_dpo_pairs_no_system_prompt

Viewer • Updated Jan 15, 2024 • 12.9k • 35 • 4

udkai/klexikon_dpo

Viewer • Updated Jan 24, 2024 • 2.89k • 33 • 3

Dahoas/rm_instruct_helpful_preferences

Viewer • Updated Mar 1, 2023 • 90.7k • 30 • 4

Dahoas/rl-prompt-dataset

Viewer • Updated Mar 17, 2023 • 207k • 31 • 2

We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs-lora

Viewer • Updated Dec 27, 2023 • 6k • 32 • 2

reciprocate/ultrafeedback_cleaned_high_dpo

Viewer • Updated Jan 11, 2024 • 40k • 35 • 2

giux78/ultrafeedback-binarized-preferences-cleaned-ita-ready

Viewer • Updated Jan 18, 2024 • 60.9k • 32 • 2

alielfilali01/ultrafeedback-arabic

Viewer • Updated Jan 31, 2024 • 63.1k • 41 • 2

AlekseyKorshuk/synthetic-instruct-gptj-pairwise

Viewer • Updated Feb 8, 2023 • 33.1k • 39 • 1

Dahoas/instruct_helpful_preferences

Viewer • Updated Mar 1, 2023 • 111k • 33 • 1

Deojoandco/reward_model_anthropic_88

Viewer • Updated Mar 26, 2023 • 8.55k • 31 • 1

SAGI-1/ultrafeedback_binarized_dpo

Viewer • Updated Nov 19, 2023 • 64k • 30 • 1

ThWu/dpo_prompt_r

Viewer • Updated Jul 1, 2024 • 183k • 42 • 1

0x7o/fialka-v2-dpo

Viewer • Updated Dec 22, 2023 • 2.47k • 29 • 1

reciprocate/ultrafeedback_cleaned_v2_dpo

Viewer • Updated Jan 8, 2024 • 58.6k • 39 • 1

nutorbit/news-headline-dpo

Viewer • Updated Jan 11, 2024 • 2.37k • 29 • 1

ayoubkirouane/Orca-Direct-Preference-Optimization

Viewer • Updated Jan 14, 2024 • 12.9k • 30 • 1

giux78/ultrafeedback-binarized-preferences-cleaned-ita

Viewer • Updated Jan 27, 2024 • 60.9k • 33 • 1

eryk-mazus/polka-dpo-v1

Viewer • Updated Jul 1, 2024 • 7.06k • 38 • 1

ZHLiu627/ultrafeedback_binarized_with_response_full_part1

Viewer • Updated Mar 8, 2024 • 20k • 33 • 1

NickyNicky/Colossal_Translation_Spanish_to_English_AND_English_to_Spanish_ORPO_DPO_Gemma

Viewer • Updated May 6, 2024 • 3.4M • 35 • 3

Baidicoot/harmful-rlhf

Viewer • Updated May 6, 2024 • 42.5k • 30 • 1

thepowerfuldeez/Qwen-summarize-dataset-train

Viewer • Updated Jul 1, 2024 • 20.4k • 43 • 1

AlekseyKorshuk/davinci-pairwise

Viewer • Updated Feb 7, 2023 • 144k • 66

AlekseyKorshuk/davinci-pairwise-all

Viewer • Updated Feb 7, 2023 • 48k • 36

AlekseyKorshuk/davinci-pairwise-tokenized

Viewer • Updated Feb 8, 2023 • 72k • 37

AlekseyKorshuk/davinci-pairwise-filtered

Viewer • Updated Feb 8, 2023 • 108k • 31

AlekseyKorshuk/chai-synthetic-pairwise

Viewer • Updated Feb 10, 2023 • 45.7k • 53

AlekseyKorshuk/cup-it-ds-pairwise-small

Viewer • Updated Mar 18, 2023 • 17.6k • 30

ummagumm-a/cup-it-ds-classification-pairwise-test

Viewer • Updated Mar 19, 2023 • 56k • 30

HuggingFaceH4/test-dataset-all-splits

Viewer • Updated Apr 25, 2023 • 600 • 43 • 1

AlekseyKorshuk/lmeh-chai-davinci

Viewer • Updated May 18, 2023 • 14.4k • 32

AlekseyKorshuk/lmeh-chai-synthetic

Viewer • Updated May 18, 2023 • 4.57k • 36

TaylorAI/rlcd

Viewer • Updated Sep 29, 2023 • 168k • 31

PanoEvJ/GPT3.5_summarization_preference_RLAIF

Viewer • Updated Oct 1, 2023 • 100 • 31

JuanKO/RLAIF_summarization_preference_gpt35

Viewer • Updated Oct 2, 2023 • 1k • 31

victorialee/openai_summarize_comparisons_relabel_GPTJ

Updated Oct 4, 2023 • 31

sayan1101/reward_test_custom_dataset_RLHF

Viewer • Updated Oct 23, 2023 • 164 • 34

vwxyzjn/cai-conversation-dev1-h4

Viewer • Updated Nov 27, 2023 • 16.4k • 35

SebastianSchramm/ultrafeedback_binarized_prefs_filtered

Viewer • Updated Nov 15, 2023 • 58.1k • 32

genta-tech/rlhf-id-30

Viewer • Updated Nov 17, 2023 • 125k • 31

orendar/ultrafeedback_binarized_filtered

Viewer • Updated Jul 4, 2024 • 27.2k • 32

remyxai/ffmperative_dpo

Viewer • Updated Nov 30, 2023 • 1.48k • 33

rajammanabrolu/ultrafeedback_binarized

Viewer • Updated Nov 30, 2023 • 190k • 47

vwxyzjn/cai-conversation-prod-h4-harmless

Viewer • Updated Dec 1, 2023 • 44.9k • 98

kfkas/test_DPO_dataset

Viewer • Updated Dec 5, 2023 • 3.83k • 31

varun-v-rao/mimic-cxr-dpo-with-metrics

Viewer • Updated Dec 10, 2023 • 125k • 41 • 1

mnoukhov/openai_summarize_generated_10k

Viewer • Updated Dec 15, 2023 • 10k • 31

mnoukhov/openai_summarize_generated_10-20k

Viewer • Updated Dec 15, 2023 • 10k • 34

mnoukhov/openai_summarize_generated_20k

Viewer • Updated Dec 18, 2023 • 20k • 33

dvilasuero/ultrafeedback-followup

Viewer • Updated Dec 19, 2023 • 6k • 28 • 1

GokhanAI/INST_Synthetic_MISTRAL

Viewer • Updated Dec 22, 2023 • 26.3k • 41

dvilasuero/multiturner

Viewer • Updated Dec 19, 2023 • 3.43k • 30

arianhosseini/openai_summarize_comparisons_relabel_pythia1b_iter1_temp0.7

Viewer • Updated Dec 22, 2023 • 20k • 33

mnoukhov/compare_results

Viewer • Updated Dec 22, 2023 • 100 • 30

mnoukhov/openai_summarize_vllm_generated_20k_label410m

Viewer • Updated Feb 5, 2024 • 19.9k • 35

reciprocate/orca_dpo_pairs

Viewer • Updated Jan 3, 2024 • 14.8k • 35

reciprocate/pku_better_dpo_pairs

Viewer • Updated Jan 3, 2024 • 330k • 29

reciprocate/pku_safer_dpo_pairs

Viewer • Updated Jan 3, 2024 • 51.8k • 36

manishiitg/jondurbin-truthy-dpo-v0.1

Viewer • Updated Jan 29, 2024 • 2.03k • 62

manishiitg/unalignment-toxic-dpo-v0.1

Viewer • Updated Jan 29, 2024 • 604 • 32

mii-llm/oasst2-dpo-it

Viewer • Updated Jan 9, 2024 • 210 • 31

vwxyzjn/cai-conversation-dev1704836562

Viewer • Updated Jan 9, 2024 • 128 • 32

UnderstandLing/oasst1_nl_threads_dpo

Viewer • Updated Jan 10, 2024 • 25.1k • 30

vwxyzjn/cai-conversation-dev1705363150

Viewer • Updated Jan 16, 2024 • 128 • 30

giux78/0-10000-ultrafeedback-binarized-preferences-cleaned-ita

Viewer • Updated Jan 16, 2024 • 10k • 30

vwxyzjn/cai-conversation-dev1705423021

Viewer • Updated Jan 16, 2024 • 2.31k • 28

vwxyzjn/cai-conversation-dev1705526305

Viewer • Updated Jan 17, 2024 • 256 • 32

CognitiveLab/hh-rlhf-formatted-60000

Viewer • Updated Jan 18, 2024 • 60k • 30

vwxyzjn/cai-conversation-dev1705620998

Viewer • Updated Jan 18, 2024 • 256 • 36

vwxyzjn/cai-conversation-dev1705631776

Viewer • Updated Jan 19, 2024 • 256 • 37

vwxyzjn/cai-conversation-dev1705676837

Viewer • Updated Jan 19, 2024 • 256 • 45

arianhosseini/trl_data

Viewer • Updated Jan 21, 2024 • 20k • 32

weijie210/UC_preference_iter_0

Viewer • Updated Jan 31, 2024 • 39.1k • 30

weijie210/UC_preference_iter_0_all

Viewer • Updated Jan 27, 2024 • 93.2k • 29

SUSTech/bagel-clean

Viewer • Updated Jan 27, 2024 • 799k • 51

weijie210/UFB_preference_iter_0_all

Viewer • Updated Jan 28, 2024 • 56.6k • 30

pvduy/dpo_data_ultra

Viewer • Updated Jan 29, 2024 • 80k • 36

ogbrandt/gpt35_preference_rlaif

Viewer • Updated Jan 29, 2024 • 520 • 29

ogbrandt/gpt4_preference_rlaif

Viewer • Updated Jan 29, 2024 • 520 • 41

Asap7772/ultrafeedback_binarized_narrow_unlabeled

Viewer • Updated Jan 29, 2024 • 60.7k • 35

Asap7772/ultrafeedback_binarized_narrow

Viewer • Updated Jan 30, 2024 • 60.7k • 33

weijie210/UFB_reference_rejected

Viewer • Updated Feb 1, 2024 • 57.6k • 29

vwxyzjn/openhermes-dev__mistralai_Mistral-7B-Instruct-v0.1__1706885528

Viewer • Updated Feb 2, 2024 • 24 • 32

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1706886961

Viewer • Updated Feb 2, 2024 • 24 • 32

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1706887930

Viewer • Updated Feb 2, 2024 • 30 • 30

nz/anthropic-hh-golden-rlhf

Viewer • Updated Feb 2, 2024 • 44.8k • 32

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1706893611

Viewer • Updated Feb 2, 2024 • 84 • 31

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1706896441

Viewer • Updated Feb 2, 2024 • 5 • 30

arianhosseini/summarize_dpo1b1_ngen10_20k

Viewer • Updated Feb 2, 2024 • 20k • 33

dkshjn/processed_truthy-v2

Viewer • Updated Feb 4, 2024 • 1.02k • 31

weijie210/UFB_prefs_iter_0_4_bestn

Viewer • Updated Feb 4, 2024 • 55.5k • 34

weijie210/UC_prefs_iter_0

Viewer • Updated Feb 5, 2024 • 31 • 29

weijie210/UFB_maximal_prefs

Viewer • Updated Feb 6, 2024 • 63.1k • 29

nz/highest-number-rlhf

Viewer • Updated Feb 7, 2024 • 84k • 33

vwxyzjn/openhermes-dev__mistralai_Mistral-7B-Instruct-v0.1__1707330518

Viewer • Updated Feb 7, 2024 • 167 • 36

vwxyzjn/openhermes-dev__mistralai_Mistral-7B-Instruct-v0.1__1707330742

Viewer • Updated Feb 7, 2024 • 167 • 33

vwxyzjn/openhermes-dev__meta-llama_Llama-2-70b-chat-hf__1707333633

Viewer • Updated Feb 7, 2024 • 167 • 33

vwxyzjn/openhermes-dev__meta-llama_Llama-2-70b-chat-hf__1707337384

Viewer • Updated Feb 7, 2024 • 167 • 35

vwxyzjn/openhermes-dev__kaist-ai_prometheus-13b-v1.0__1707405480

Viewer • Updated Feb 8, 2024 • 167 • 39

vwxyzjn/openhermes-dev__kaist-ai_prometheus-13b-v1.0__1707406141

Viewer • Updated Feb 8, 2024 • 167 • 34

vwxyzjn/openhermes-dev__kaist-ai_prometheus-13b-v1.0__1707408224

Viewer • Updated Feb 8, 2024 • 167 • 32

weijie210/gsm8k_dpo

Viewer • Updated Feb 9, 2024 • 5.48k • 38

vwxyzjn/openhermes-dev__kaist-ai_prometheus-13b-v1.0__1707422187

Viewer • Updated Feb 9, 2024 • 48.3k • 32

shidowake/UFeedback_without_gpt_output

Viewer • Updated Feb 9, 2024 • 7.68k • 34

nz/100_rlhf

Viewer • Updated Feb 11, 2024 • 107k • 32

ibndias/distilabel-capybara-dpo-7k-binarized

Viewer • Updated Feb 14, 2024 • 7.56k • 32

vwxyzjn/ultrafeedback_binarized_1707920039

Viewer • Updated Feb 14, 2024 • 2k • 33

dlibf/ultra_feedback_zephyr-dpo

Viewer • Updated Feb 15, 2024 • 125k • 40

dlibf/ultra_feedback_zephyr-sft

Viewer • Updated Feb 15, 2024 • 125k • 37

vwxyzjn/ultrafeedback_binarized_1707945637

Viewer • Updated Feb 14, 2024 • 63.1k • 37

vwxyzjn/ultrafeedback_binarized_1707947544

Viewer • Updated Feb 14, 2024 • 63.1k • 38

arianhosseini/comparisons_20k_regen_labeled_dpo1b1

Viewer • Updated Feb 15, 2024 • 20k • 32

male-2/0.2.0-public

Viewer • Updated Feb 17, 2024 • 1 • 32

macadeliccc/distilabel-neurology-preferences-2k-cleaner

Viewer • Updated Jul 4, 2024 • 1.99k • 37

mnoukhov/openai_summarize_comparisons_tldprompt_relabel_pythia410m-dpo1

Viewer • Updated Feb 19, 2024 • 92.5k • 37

vwxyzjn/ultrafeedback_binarized_1708381525

Viewer • Updated Feb 19, 2024 • 1.9k • 35

Radiantloom/distilabel-intel-orca-dpo-pairs-chatml

Viewer • Updated Feb 20, 2024 • 12.9k • 33

cassanof/python_pass_fail_sample

Viewer • Updated Feb 20, 2024 • 100 • 32

sanduntg/cpcdata_ppo

Viewer • Updated Feb 21, 2024 • 24 • 33

cmcmaster/OpenHermes2.5-dpo-binarized-alpha-trl

Viewer • Updated Feb 22, 2024 • 9.79k • 30

mnoukhov/openai_summarize_generated_20k_relabel_1b_margin

Viewer • Updated Feb 22, 2024 • 20k • 33

mnoukhov/openai_summarize_comparisons_tldrprompt_relabel1b_margin

Viewer • Updated Feb 22, 2024 • 97.5k • 32

mnoukhov/compare_test

Viewer • Updated Feb 26, 2024 • 20k • 29

mnoukhov/summarize_from_feedback_tldr3_generated_20k_vllm_pythia1b_dpo

Viewer • Updated Feb 26, 2024 • 20k • 30

mnoukhov/summarize_from_feedback_tldr3_generated_20k_relabel_pythia1b_dpo

Viewer • Updated Feb 26, 2024 • 20k • 33

mnoukhov/openai_summarize_generated_20k_relabel_1b_predict_410m-dpo1

Viewer • Updated Feb 26, 2024 • 20k • 29

NickyNicky/distilabel-intel-orca-dpo-pairs_gemma_chatml

Viewer • Updated Feb 26, 2024 • 12.9k • 29

celinelee/thestack_py312_fstrings_dpo

Viewer • Updated Feb 29, 2024 • 100k • 28

cnbeining/sentence-segmentation-dpo-raw

Viewer • Updated Feb 29, 2024 • 9.18k • 39

Baidicoot/anthropic_hh_golden_llama

Viewer • Updated Mar 1, 2024 • 42.1k • 31

aengusl/llama_dpo_hhh

Viewer • Updated Mar 1, 2024 • 161k • 28

aengusl/mistral_dpo_hhh

Viewer • Updated Mar 1, 2024 • 161k • 28

arianhosseini/summ_dpo1b1_ngen10_minmax

Viewer • Updated Mar 10, 2024 • 20k • 36

Baidicoot/dpo_safety_ihy_openhermes

Viewer • Updated Mar 3, 2024 • 5k • 30

celinelee/thestack_npzeros_dpo

Viewer • Updated Mar 3, 2024 • 100k • 28

nz/closest_to_5000_range_1000_to_9000_55k

Viewer • Updated Mar 6, 2024 • 55.7k • 30

ZHLiu627/ultrafeedback_binarized_with_response_full_part0

Viewer • Updated Mar 7, 2024 • 20k • 33

David-Xu/astronomy-stack-cira

Viewer • Updated Mar 8, 2024 • 19.9k • 29

ZHLiu627/ultrafeedback_binarized_with_response_full_part2

Viewer • Updated Mar 8, 2024 • 21.1k • 31

ZHLiu627/ultrafeedback_binarized_with_response_full

Viewer • Updated Mar 8, 2024 • 61.1k • 33

David-Xu/astronomy-stack-dpo-20-percent

Viewer • Updated Mar 10, 2024 • 3.99k • 30

aengusl/noise0_alpaca_sleeper_agents_toy_test_preference_v4

Viewer • Updated Mar 11, 2024 • 15.7k • 31

vwxyzjn/ultrafeedback_binarized_1710165338

Viewer • Updated Mar 11, 2024 • 25k • 28

aengusl/train_hp_dpo_unlrn_ds

Viewer • Updated Mar 11, 2024 • 927 • 32

vtiyyal1/AskDocsEmpathy_2k_dpo

Viewer • Updated Mar 13, 2024 • 2.12k • 31

vtiyyal1/AskDocsEmpathy_2k_llama_dpo

Viewer • Updated Mar 13, 2024 • 2.12k • 27

davidberenstein1957/ultrafeedback-binarized-cleaned-and-filtered-random-split

Viewer • Updated Mar 14, 2024 • 6.69k • 33

manishiitg/aditi-dpo-prompts

Viewer • Updated Apr 8, 2024 • 48.7k • 38 • 1

mesolitica/DPO-malaysian-questions

Viewer • Updated Mar 20, 2024 • 32.5k • 34

mesolitica/DPO-translated-CodeUltraFeedback

Viewer • Updated Apr 1, 2024 • 7.17k • 36

Nbardy/prompt_variance_reward_complete

Viewer • Updated Mar 27, 2024 • 412 • 30

orpo-explorers/OpenHermesPreferences-100k

Viewer • Updated Mar 30, 2024 • 100k • 30

ShenaoZ/ultrafeedback_subset

Viewer • Updated Apr 3, 2024 • 22k • 32

ShenaoZhang/0.001_idpo_same_nodpo_dataset

Viewer • Updated Apr 6, 2024 • 67.1k • 33

ShenaoZhang/0.001_idpo_same_replacechosen_dataset

Viewer • Updated Apr 6, 2024 • 44.8k • 32

dinaaaaaa/lima_rand_sel_50_preference_self_reward

Viewer • Updated Sep 26, 2024 • 223 • 28

AnushaKulkarni/preferred_dataset

Viewer • Updated Apr 7, 2024 • 50 • 29

ShenaoZhang/0.001_idpo_noreplacerej_ref_response

Viewer • Updated Apr 8, 2024 • 44.8k • 31

ShenaoZhang/0.001_idpo_noreplacerej_dataset

Viewer • Updated Apr 10, 2024 • 44.8k • 34

Jessiecs/7374-assignment4-question2_dataset_for_DPO

Viewer • Updated Apr 7, 2024 • 50 • 28

jinlibao/lima_preference_dataset

Viewer • Updated Apr 8, 2024 • 50 • 28

ShenaoZhang/0.0005_idpo_same_nodpo_replace_dataset

Viewer • Updated Apr 10, 2024 • 67.1k • 33

thavens/ufb_mini

Viewer • Updated Apr 11, 2024 • 160 • 32

hsikchi/tldr-preference-trl-style

Viewer • Updated Apr 12, 2024 • 179k • 45

gx-ai-architect/helpsteer_preference

Viewer • Updated Apr 12, 2024 • 35.6k • 36

sophiex/hh-rlhf

Viewer • Updated Apr 12, 2024 • 169k • 31

ShenaoZ/0.0001_idpo_same_3iters_dataset

Viewer • Updated Apr 13, 2024 • 44.8k • 33

guoyu-zhang/hh_llama2

Viewer • Updated Apr 13, 2024 • 125k • 37

ShenaoZ/0.0_idpo_same_3iters_debug_dataset

Viewer • Updated Apr 14, 2024 • 22.4k • 29

guoyu-zhang/shp_1

Viewer • Updated Apr 15, 2024 • 1k • 31

guoyu-zhang/shp_2

Viewer • Updated Apr 15, 2024 • 1k • 28

guoyu-zhang/shp_3

Viewer • Updated Apr 15, 2024 • 1k • 30

when2rl/OpenHermesPreferences_reformatted

Viewer • Updated Apr 17, 2024 • 985k • 28

mnoukhov/summarize_from_feedback_tldr3_generated_relabel_20k_dpo_costa_1b_fp16.yml_3d94f50_b35a8

Viewer • Updated Apr 16, 2024 • 20k • 35

ShenaoZ/0.0_ablation_4iters_dataset

Viewer • Updated Apr 17, 2024 • 17.3k • 29

ShenaoZ/0.001_ablation_4iters_dataset

Viewer • Updated Apr 17, 2024 • 17.3k • 27

ShenaoZ/0.000001_ablation_dataset

Viewer • Updated Apr 18, 2024 • 44.8k • 30

ShenaoZ/0.0_ablation_6iters_dataset

Viewer • Updated Apr 18, 2024 • 48.8k • 28

ShenaoZ/0.0_ablation_dataset

Viewer • Updated Apr 18, 2024 • 44.8k • 31

UCLAML/snorkel_prompt3

Viewer • Updated Apr 18, 2024 • 21k • 30

mnoukhov/summarize_from_feedback_tldr3_generated_relabel_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 18, 2024 • 20k • 36

arianhosseini/hh_with_prompt

Viewer • Updated Apr 18, 2024 • 169k • 30

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 19, 2024 • 107k • 39

when2rl/OpenHermesPreferences_CamelAI

Viewer • Updated Apr 19, 2024 • 78.4k • 31

Louieworth/hh-rlhf-trl-style

Viewer • Updated Apr 20, 2024 • 100 • 30

rippertnt/OpenOrca-dpo-ko-en

Viewer • Updated Apr 21, 2024 • 25.6k • 35

dmvaldman/showerthought_preferences2

Viewer • Updated Apr 23, 2024 • 34k • 28

Astris/toxic-dpo-v0.2-embedded

Updated Apr 22, 2024 • 31

YYYYYYibo/ultrafeedback_binarized_with_response_full

Viewer • Updated Apr 22, 2024 • 61.1k • 30

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_dpo_costa_2.8b_bf16.yml_6e799

Viewer • Updated Apr 22, 2024 • 107k • 31

orpo-explorers/OHP-Stratified-1

Viewer • Updated Apr 22, 2024 • 327k • 31

ShenaoZ/0.001_ablation_4iters_bs512_dataset

Viewer • Updated Apr 22, 2024 • 2k • 31

ShenaoZ/0.001_ablation_4iters_bs256_declr_dataset

Viewer • Updated Apr 23, 2024 • 51.8k • 30

ShenaoZ/0.01_ablation_5iters_bs256_nodpo_dataset

Viewer • Updated Apr 24, 2024 • 71.1k • 31

ShenaoZ/0.01_ablation_4iters_bs256_nodpo_dataset

Viewer • Updated Apr 24, 2024 • 69.1k • 39

ShenaoZ/0.001_ablation_4iters_bs256_nodpo_sample2_dataset

Viewer • Updated Apr 25, 2024 • 69.1k • 32

YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_0

Viewer • Updated Apr 24, 2024 • 10k • 29

YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_1

Viewer • Updated Apr 24, 2024 • 10k • 31

YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_2

Viewer • Updated Apr 24, 2024 • 10k • 31

YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_3

Viewer • Updated Apr 24, 2024 • 10k • 30

YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_4

Viewer • Updated Apr 24, 2024 • 10k • 30

YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_5

Viewer • Updated Apr 24, 2024 • 10k • 30

orpo-explorers/OHP-15k-mathcode

Viewer • Updated Apr 24, 2024 • 15k • 30 • 1

ShenaoZ/0.001_ablation_3iters_bs256_nodpo_dataset

Viewer • Updated Apr 25, 2024 • 67.1k • 31

ShenaoZ/0.001_ablation_5iters_bs256_nodpo_dataset

Viewer • Updated Apr 24, 2024 • 71.1k • 30

ShenaoZhang/0.001_ablation_4iters_bs128_nodpo_dataset

Viewer • Updated Apr 25, 2024 • 69.1k • 32

ShenaoZhang/0.0_ablation_4iters_bs128_nodpo_dataset

Viewer • Updated Apr 25, 2024 • 53.8k • 33

ShenaoZhang/0.01_ablation_4iters_bs128_nodpo_dataset

Viewer • Updated Apr 25, 2024 • 53.8k • 44

ShenaoZ/0.01_ablation_3iters_bs256_nodpo_dataset

Viewer • Updated Apr 25, 2024 • 42.8k • 33

ShenaoZ/0.001_ablation_4iters_bs256_nodpo_useresponse_dataset

Viewer • Updated Apr 25, 2024 • 69.1k • 32

YYYYYYibo/ultrafeedback_binarized_without_ranked

Viewer • Updated Apr 25, 2024 • 10k • 27

NickyNicky/DPO_tokenizer_phi_3_test

Viewer • Updated Apr 26, 2024 • 10 • 31

lightblue/mitsu_top25_borda

Viewer • Updated May 30, 2024 • 674 • 54

ShenaoZ/0.001_3iters_bs128_declr_nodpo_dataset

Viewer • Updated Apr 26, 2024 • 24.4k • 30

ShenaoZ/0.001_3iters_bs128_declr_nodpo_zephyrbeta_dataset

Viewer • Updated Apr 26, 2024 • 46.8k • 33

YYYYYYibo/ultrafeedback_binarized_phase_0_part_0

Viewer • Updated Apr 26, 2024 • 100 • 28

ShenaoZhang/0.001_5iters_bs256_nodpo_only4w_dataset

Viewer • Updated Apr 28, 2024 • 70k • 41

YYYYYYibo/ultrafeedback_binarized_phase_1_part_1_part1

Viewer • Updated Apr 27, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_phase_1_part_1_part0

Viewer • Updated Apr 27, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_phase_1_part_1_minpi

Viewer • Updated Apr 27, 2024 • 10k • 32

ShenaoZhang/0.1_4iters_bs256_nodpo_only4w_dataset

Viewer • Updated Apr 27, 2024 • 48k • 29

ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_dataset

Viewer • Updated Apr 28, 2024 • 46k • 31

YYYYYYibo/ultrafeedback_binarized_phase_2

Viewer • Updated Apr 28, 2024 • 20k • 30

YYYYYYibo/ultrafeedback_binarized_phase_2_part_1minipart_1

Viewer • Updated Apr 28, 2024 • 1k • 30

YYYYYYibo/ultrafeedback_binarized_phase_2_unranked

Viewer • Updated Apr 28, 2024 • 9.28k • 28

YYYYYYibo/ultrafeedback_binarized_phase_2_minpi

Viewer • Updated Apr 28, 2024 • 9.28k • 31

ShenaoZhang/0.001_6iters_bs256_nodpo_full6w_dataset

Viewer • Updated Apr 28, 2024 • 2k • 29

ShenaoZhang/0.01_3iters_bs256_nodpo_full6w_dataset

Viewer • Updated Apr 29, 2024 • 67.1k • 36

communityai/system_identity_remove_preference_meta_ai

Viewer • Updated Apr 28, 2024 • 93 • 30

communityai/system_identity_remove_preference_google

Viewer • Updated Apr 28, 2024 • 93 • 28

communityai/system_identity_remove_preference_facebook

Viewer • Updated Apr 28, 2024 • 93 • 30

communityai/system_identity_remove_preference_alibaba

Viewer • Updated Apr 28, 2024 • 93 • 30

communityai/system_identity_remove_preference_alibaba_cloud

Viewer • Updated Apr 28, 2024 • 93 • 31

communityai/system_identity_remove_preference_mistral

Viewer • Updated Apr 28, 2024 • 93 • 30

communityai/system_identity_remove_preference_cohere

Viewer • Updated Apr 28, 2024 • 93 • 29

communityai/system_identity_remove_preference_chatgpt

Viewer • Updated Apr 28, 2024 • 93 • 30

communityai/system_identity_remove_preference_gpt

Viewer • Updated Apr 28, 2024 • 93 • 28

communityai/system_identity_remove_preference_gpt_3

Viewer • Updated Apr 28, 2024 • 93 • 28

communityai/system_identity_remove_preference_gpt_4

Viewer • Updated Apr 28, 2024 • 93 • 30

YYYYYYibo/ultrafeedback_binarized_phase_3

Viewer • Updated Apr 29, 2024 • 21.1k • 29

ShenaoZhang/0.001_2iters_bs256_nodpo_full6w_dataset

Viewer • Updated Apr 29, 2024 • 65.1k • 31

YYYYYYibo/first-eval-dataset-no-score

Viewer • Updated Apr 29, 2024 • 1k • 30

YYYYYYibo/first-dpo-eval-dataset-no-score

Viewer • Updated Apr 29, 2024 • 1k • 30

ShenaoZhang/0.0_3iters_bs256_nodpo_full6w_dataset

Viewer • Updated Apr 29, 2024 • 44.8k • 29

ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_dataset

Viewer • Updated Apr 29, 2024 • 34.6k • 35

C-Stuti/llama3-8b-orpo-con

Viewer • Updated Apr 29, 2024 • 3.36k • 38

Ksgk-fy/alignment-dpo-test2-mode-3

Viewer • Updated Apr 30, 2024 • 720 • 35

Ksgk-fy/alignment-dpo-test2-mode-4

Viewer • Updated Apr 30, 2024 • 720 • 30

YYYYYYibo/ultrafeedback_binarized_vllm_part_2

Viewer • Updated May 1, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_minpi_part_2

Viewer • Updated May 1, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_train_part_2

Viewer • Updated May 1, 2024 • 25k • 31

ReBatch/ultrafeedback_binarized_nl

Viewer • Updated May 30, 2024 • 61.7k • 30

YYYYYYibo/ultrafeedback_binarized_minpi_part_3

Viewer • Updated May 1, 2024 • 5k • 35

nbalepur/Mnemonic_Preferences_direct_comparison_fixed

Preview • Updated Apr 30, 2024 • 34

jhmejia/classifai

Viewer • Updated May 1, 2024 • 99 • 55

YYYYYYibo/whatever

Viewer • Updated May 1, 2024 • 40 • 30

GENIAC-Team-Ozaki/chatbot-arena-ja-calm2-7b-chat-experimental_deduped

Viewer • Updated May 2, 2024 • 23.3k • 35

YYYYYYibo/eval-dataset-merge

Viewer • Updated May 2, 2024 • 1k • 28

YYYYYYibo/eval-dataset-rank4

Viewer • Updated May 3, 2024 • 200 • 28

YYYYYYibo/eval-dataset-with-score-original

Viewer • Updated May 2, 2024 • 200 • 31

YYYYYYibo/eval-dataset-with-score-vanilla

Viewer • Updated May 2, 2024 • 200 • 29

YYYYYYibo/ultrafeedback_binarized_plus_left_part_3

Viewer • Updated May 3, 2024 • 16.1k • 29

YYYYYYibo/ultrafeedback_binarized_plus_train_part_3

Viewer • Updated May 3, 2024 • 5k • 29

ShenaoZ/0.0001_withdpo_3iters_bs256_511lr_dataset

Viewer • Updated May 3, 2024 • 44.8k • 30

hanyinwang/layer-project-reward-training

Viewer • Updated May 3, 2024 • 101 • 27

vipinkatara/dataset_complete_new

Viewer • Updated May 3, 2024 • 89.5k • 29

YYYYYYibo/eval-dataset-with-score-rank4_plus

Viewer • Updated May 3, 2024 • 200 • 31

vipinkatara/dataset_complete_final

Viewer • Updated May 3, 2024 • 89.5k • 32

YYYYYYibo/ultrafeedback_binarized_epoch_2_vllm_part_1

Viewer • Updated May 3, 2024 • 5k • 28

YYYYYYibo/ultrafeedback_binarized_epoch_2_left_part_1

Viewer • Updated May 3, 2024 • 16.1k • 29

ShenaoZ/0.01_withdpo_4iters_bs256_5102lr_misit_dataset

Viewer • Updated May 4, 2024 • 51.8k • 30

YYYYYYibo/ultrafeedback_binarized_epoch_2_left_part_2

Viewer • Updated May 3, 2024 • 15k • 30

YYYYYYibo/ultrafeedback_binarized_epoch_2_left_part_3

Viewer • Updated May 4, 2024 • 15k • 30

YYYYYYibo/ultrafeedback_binarized_epoch_2_train_part_3

Viewer • Updated May 4, 2024 • 26.1k • 28

YYYYYYibo/ultrafeedback_binarized_rank4_all_vllm_part_2_mini_2

Viewer • Updated May 4, 2024 • 3.8k • 29

ShenaoZ/0.001_withdpo_4iters_bs256_5102lr_dataset

Viewer • Updated May 5, 2024 • 51.8k • 29

ShenaoZ/0.00005_withdpo_4iters_bs256_5102lr_dataset

Viewer • Updated May 5, 2024 • 51.8k • 34

ShenaoZ/0.0_withdpo_4iters_bs256_5102lr_dataset

Viewer • Updated May 7, 2024 • 51.8k • 53

YYYYYYibo/ultrafeedback_binarized_rank4_all_train_part_2

Viewer • Updated May 4, 2024 • 18.6k • 29

KaggleMasterX/DPO_Test_ORPO

Viewer • Updated May 5, 2024 • 500 • 33

YYYYYYibo/ultrafeedback_binarized_rank4_all_minpi_part_3

Viewer • Updated May 5, 2024 • 20.5k • 29

KaggleMasterX/ORPO_5K

Viewer • Updated May 5, 2024 • 15k • 31

ShenaoZ/0.0001_zephyrdpoinit_nodpo_3iters_bs256_555lr_dataset

Viewer • Updated May 6, 2024 • 67.1k • 34

AmberYifan/safetyQA_DPO

Viewer • Updated May 5, 2024 • 55k • 50

ShenaoZ/0.0001_zephyrgemmasft_withdpo_3iters_bs256_555lr_dataset

Viewer • Updated May 6, 2024 • 24.4k • 31

ShenaoZ/0.0001_zephyrgemmadpo_nodpo_3iters_bs256_555lr_dataset

Viewer • Updated May 6, 2024 • 22.4k • 29

YYYYYYibo/ultrafeedback_binarized_new_train_part_1

Viewer • Updated May 6, 2024 • 15k • 30

YYYYYYibo/ultrafeedback_binarized_new_train_part_2

Viewer • Updated May 6, 2024 • 15k • 30

YYYYYYibo/ultrafeedback_binarized_new_train_part_3

Viewer • Updated May 6, 2024 • 15k • 30

YYYYYYibo/ultrafeedback_binarized_new_gen_part_1

Viewer • Updated May 6, 2024 • 5k • 29

ashishkgpian/kaggle_comp_dpo

Viewer • Updated May 6, 2024 • 39.7k • 41

Baidicoot/hh-rlhf-harmful-responses

Viewer • Updated May 6, 2024 • 14.9k • 30

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part0_mini_0

Viewer • Updated May 6, 2024 • 4.9k • 30

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part0_mini_2

Viewer • Updated May 6, 2024 • 4.9k • 30

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part0_mini_1

Viewer • Updated May 6, 2024 • 4.9k • 28

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part1_mini_1

Viewer • Updated May 6, 2024 • 4.9k • 30

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part2_mini_0

Viewer • Updated May 6, 2024 • 5.18k • 31

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part2_mini_2

Viewer • Updated May 6, 2024 • 5.18k • 32

ShenaoZ/0.0001_sft_nodpo_4iters_bs256_555lr_dataset

Viewer • Updated May 7, 2024 • 69.1k • 35 • 1

ShenaoZ/0.0001_sft_nodpo_5iters_bs256_555lr_dataset

Viewer • Updated May 7, 2024 • 71.1k • 48

ShenaoZ/0.001_sft_nodpo_3iters_bs256_531lr_dataset

Viewer • Updated May 7, 2024 • 67.1k • 35

ShenaoZ/0.001_withdpo_4iters_bs256_531lr_dataset

Viewer • Updated May 7, 2024 • 51.8k • 33

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_2_mini_3

Viewer • Updated May 7, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_2_mini_0

Viewer • Updated May 7, 2024 • 5k • 29

theGhoul21/irpo-dataset-v2

Viewer • Updated Aug 6, 2024 • 17.9k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_2_mini_2

Viewer • Updated May 7, 2024 • 4.78k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_2_mini_3

Viewer • Updated May 7, 2024 • 4.78k • 29

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_2_mini_1

Viewer • Updated May 7, 2024 • 4.78k • 30

massimilianowosz/japanese_food

Viewer • Updated May 7, 2024 • 4.69k • 30

ShenaoZ/0.0001_sft_nodpo_3iters_bs256_5102lr_dataset

Viewer • Updated May 8, 2024 • 67.1k • 31

ShenaoZ/0.0001_sft_nodpo_4iters_bs256_5102lr_dataset

Viewer • Updated May 8, 2024 • 69.1k • 29

ShenaoZ/0.0001_withdpo_5iters_bs256_5102lr_dataset

Viewer • Updated May 8, 2024 • 56.9k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_3_mini_0

Viewer • Updated May 8, 2024 • 5.28k • 29

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_3_mini_1

Viewer • Updated May 8, 2024 • 5.28k • 33

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_3_mini_0

Viewer • Updated May 8, 2024 • 5.18k • 33

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_3_mini_2

Viewer • Updated May 8, 2024 • 5.18k • 27

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_3_mini_3

Viewer • Updated May 8, 2024 • 5.19k • 31

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_3

Viewer • Updated May 8, 2024 • 20.7k • 29

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_2_mini_0

Viewer • Updated May 8, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2

Viewer • Updated May 9, 2024 • 19.4k • 32

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_2

Viewer • Updated May 9, 2024 • 4.98k • 31

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_3

Viewer • Updated May 9, 2024 • 5.09k • 27

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_1

Viewer • Updated May 9, 2024 • 5.28k • 30

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_0

Viewer • Updated May 9, 2024 • 5.28k • 31

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_minpi_part_3

Viewer • Updated May 9, 2024 • 20.6k • 29

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_3

Viewer • Updated May 9, 2024 • 5.16k • 30

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_2

Viewer • Updated May 9, 2024 • 5.16k • 29

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3

Viewer • Updated May 9, 2024 • 20.6k • 30

ShenaoZ/0.001_withdpo_4iters_bs256_5551lr_dataset

Viewer • Updated May 10, 2024 • 51.8k • 31

ShenaoZ/0.0005_mistral_withdpo_4iters_bs256_5551lr_dataset

Viewer • Updated May 10, 2024 • 51.8k • 29

Baidicoot/anthropic-rlhf-eval

Viewer • Updated May 10, 2024 • 2.31k • 46

GENIAC-Team-Ozaki/chatbot-arena-ja-calm2-7b-chat-experimental_deduped_add_generated_text

Viewer • Updated May 14, 2024 • 12k • 54

euiyulsong/arc_train_ds

Viewer • Updated May 17, 2024 • 1.12k • 33

ShenaoZhang/0.001_zephyr_5551_4iters_bs256_dataset

Viewer • Updated May 13, 2024 • 51.8k • 37

Code-Refinement/dpo-sample-perfect-less

Viewer • Updated May 14, 2024 • 128 • 34

Code-Refinement/dpo-sample-perfect-more

Viewer • Updated May 14, 2024 • 128 • 29

reciprocate/dpo-objective

Viewer • Updated May 14, 2024 • 512 • 34

ShenaoZhang/0.01_zephyr_5551_4iters_bs256_dataset

Viewer • Updated May 15, 2024 • 51.8k • 36

euiyulsong/sciqa_train_ds_random_rejected

Viewer • Updated May 15, 2024 • 12.7k • 60

GENIAC-Team-Ozaki/chatbot-arena-ja-karakuri-lm-8x7b-chat-v0.1-awq

Viewer • Updated May 17, 2024 • 12.5k • 116

euiyulsong/threedata

Viewer • Updated May 17, 2024 • 5.7k • 29

euiyulsong/arc_all

Viewer • Updated May 17, 2024 • 3.36k • 29

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_pythia410m-dpo-tldr_relabel_pythia1b

Viewer • Updated May 17, 2024 • 107k • 33

DuongTrongChi/detoxic

Viewer • Updated May 17, 2024 • 5.69k • 30

euiyulsong/generated_data_all_cos

Viewer • Updated May 18, 2024 • 3.32k • 32

theGhoul21/irpo-dataset-v3-iteration2

Viewer • Updated May 18, 2024 • 5.01k • 38

euiyulsong/generated_data_all_cos_3000

Viewer • Updated May 18, 2024 • 3k • 31

JiazhenLiu01/dpo_llama3_362_threeturn

Viewer • Updated May 19, 2024 • 1.46k • 29

JiazhenLiu01/dpo_llama3_362_threeturn_empty_neg

Viewer • Updated May 19, 2024 • 1.46k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_1

Viewer • Updated May 19, 2024 • 20k • 33

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.20

Updated May 20, 2024 • 32

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.10

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.00

Updated May 20, 2024 • 28

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.00

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.20

Updated May 20, 2024 • 33

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.20

Updated May 20, 2024 • 27

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.30

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.10

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.00

Updated May 20, 2024 • 32

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.10

Updated May 20, 2024 • 33

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.20

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.20

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.30

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.20

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.30

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.00

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.10

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.20

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.20

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.40

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.20

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.10

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.50

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.40

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.30

Updated May 20, 2024 • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_1_mini_1

Viewer • Updated May 20, 2024 • 5k • 30

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.50

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.40

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.30

Updated May 20, 2024 • 28

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.30

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.30

Updated May 20, 2024 • 28

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.40

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.50

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.50

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.40

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.40

Updated May 20, 2024 • 28

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.50

Updated May 20, 2024 • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_2_mini_1

Viewer • Updated May 20, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_2_mini_3

Viewer • Updated May 20, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_2_mini_2

Viewer • Updated May 20, 2024 • 5k • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_2_mini_0

Viewer • Updated May 20, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_2_mini_3

Viewer • Updated May 20, 2024 • 5k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_2

Viewer • Updated May 20, 2024 • 20k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_3_mini_3

Viewer • Updated May 20, 2024 • 5.29k • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_3_mini_2

Viewer • Updated May 20, 2024 • 5.28k • 32

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_3_mini_0

Viewer • Updated May 20, 2024 • 5.28k • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_3_mini_1

Viewer • Updated May 20, 2024 • 5.28k • 30

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_3_mini_3

Viewer • Updated May 20, 2024 • 5.29k • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_3_mini_2

Viewer • Updated May 20, 2024 • 5.28k • 30

mcding-org/CorrectDPO-Dataset-U0

Updated May 21, 2024 • 29

yasirchemmakh/dpo_llama3

Viewer • Updated May 21, 2024 • 43 • 30

mcding-org/CorrectDPO-Eval-DDP_L8B_U0_beta0.10r0.30rho0.20

Updated May 21, 2024 • 28

mnlp-nsoai/hf-dpo-pairs-collection

Viewer • Updated May 23, 2024 • 10.5k • 37

Piteryo/count_letters

Viewer • Updated May 23, 2024 • 1.28k • 28 • 1

rafaelsandroni/ultrafeedback_binarized_translated

Viewer • Updated May 23, 2024 • 1 • 32

GENIAC-Team-Ozaki/tuninig-dataset_pref_20pct_v3_full-sft-finetuned-stage4-iter86000-v3

Viewer • Updated May 24, 2024 • 19.3k • 30

Piteryo/exact_number_of_sentences

Viewer • Updated May 24, 2024 • 1.28k • 41

GENIAC-Team-Ozaki/tuninig-dataset_pref_20pct_v4_full-sft-finetuned-stage4-iter86000-v4

Viewer • Updated May 25, 2024 • 19.5k • 29

berquetR/dpo_preference_dataset_EPFL_shp

Viewer • Updated May 26, 2024 • 69.1k • 28

ReBatch/ultrafeedback_nl

Viewer • Updated May 30, 2024 • 71.4k • 28

ShenaoZ/SELM-Zephyr-7B-dataset

Viewer • Updated May 31, 2024 • 17.3k • 30

nhyha/DPO

Viewer • Updated Jun 12, 2024 • 1 • 33

nhyha/ORPO_2

Viewer • Updated Jun 12, 2024 • 4 • 33

SiMajid/Dahoad

Viewer • Updated Jun 17, 2024 • 2.96k • 29

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_2_mini_3

Viewer • Updated Jun 17, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_2_mini_1

Viewer • Updated Jun 17, 2024 • 5k • 30

minkyungpark/UFB_test

Viewer • Updated Jul 4, 2024 • 2k • 32

mnoukhov/summarize_from_feedback_oai_preprocessing_1706381144_relabel_llama8b

Viewer • Updated Jun 19, 2024 • 176k • 32

vwxyzjn/sentiment-trl-style

Viewer • Updated Jun 20, 2024 • 100 • 32

M4-ai/prm_dpo_pairs

Viewer • Updated Jul 1, 2024 • 93.9k • 40 • 7

kashif/nectar_dpo_pairs

Viewer • Updated Dec 1, 2023 • 3.84M • 341 • 4

sablo/oasst2_dpo_pairs_en

Viewer • Updated Feb 20, 2024 • 5.12k • 50 • 2

NickyNicky/oasst2_orpo_mix_function_call_phi_3_v1

Viewer • Updated May 2, 2024 • 120k • 32 • 2

Deojoandco/reward_model_anthropic_8

Viewer • Updated Mar 26, 2023 • 8.55k • 30 • 1

FredrikBL/Legal-Snigel-DPO

Viewer • Updated May 27, 2024 • 2k • 33 • 1

nayohan/SentimentSynth-ko

Viewer • Updated Jun 30, 2024 • 5.3k • 32 • 1

LawChat-tw/RLHF_data

Viewer • Updated Aug 18, 2023 • 23.6k • 79

cryptom/rm-static

Updated Nov 5, 2023 • 37

mnoukhov/openai_summarize_vllm_generated_20k

Viewer • Updated Dec 25, 2023 • 19.9k • 40

dvilasuero/multiturner-for-generation

Viewer • Updated Dec 19, 2023 • 3.43k • 36

Jaredquek/DpoOlier

Viewer • Updated Jan 12, 2024 • 315 • 32

vwxyzjn/cai-conversation-dev1705622085

Viewer • Updated Jan 19, 2024 • 44.8k • 37

vwxyzjn/cai-conversation-dev1705634160

Viewer • Updated Jan 19, 2024 • 256 • 41

vwxyzjn/cai-conversation-dev1705674984

Viewer • Updated Jan 19, 2024 • 256 • 44

vwxyzjn/cai-conversation-dev1705675844

Viewer • Updated Jan 19, 2024 • 256 • 29

weijie210/UFB_preference_iter_0

Viewer • Updated Jan 28, 2024 • 15.4k • 32

manishiitg/HuggingFaceH4-orca_dpo_pairs

Viewer • Updated Jan 29, 2024 • 22.7k • 30

pvduy/dpo_data_baai_50k

Viewer • Updated Jan 30, 2024 • 54.4k • 38

NobodyExistsOnTheInternet/FilteredTruthyDPO

Viewer • Updated Jan 31, 2024 • 477 • 38

lmg-anon/VNTL-v2.5-1.6k-dpo-pairs

Viewer • Updated Feb 2, 2024 • 8.99k • 33

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__1706888126

Viewer • Updated Feb 2, 2024 • 84 • 30

alvarobartt/orca_dpo_pairs_openai

Viewer • Updated Feb 6, 2024 • 12.9k • 29

vwxyzjn/openhermes-dev__mistralai_Mixtral-8x7B-Instruct-v0.1__temp

Viewer • Updated Feb 6, 2024 • 600k • 37

mesolitica/DPO-filtered-aya_dataset-zsm

Viewer • Updated Feb 13, 2024 • 10.1k • 38

nz/losest_to_3000_range_1000_to_9000

Viewer • Updated Mar 2, 2024 • 11k • 37

Baidicoot/dpo_safety_ihy_llama

Viewer • Updated Mar 3, 2024 • 5k • 28

kyujinpy/Mistral-EN-DPO-9K

Viewer • Updated Jul 6, 2024 • 9.18k • 34

vwxyzjn/ultrafeedback_binarized_1710204240

Viewer • Updated Mar 12, 2024 • 24.9k • 33

ShenaoZhang/0.001_idpo_4iters_dataset

Viewer • Updated Apr 6, 2024 • 51.8k • 30

mnoukhov/summarize_from_feedback_tldr3_generated_20k_relabel_pythia1b_dpo_temp0.7

Viewer • Updated Apr 8, 2024 • 20k • 34

Joyqiuyue/lima-preference_dataset-2

Viewer • Updated Apr 8, 2024 • 1 • 31

ShenaoZ/0.001_idpo_same_scratch_ref_dataset

Viewer • Updated Apr 13, 2024 • 63.1k • 30

AY2324S2-CS4248-Team-47/gec-dpo-ultrafeedback

Viewer • Updated Apr 16, 2024 • 2k • 29

when2rl/truthy-dpo-v0.1_reformatted

Viewer • Updated Apr 17, 2024 • 1.02k • 33

ShenaoZ/0.001_ablation_6iters_dataset

Viewer • Updated Apr 18, 2024 • 48.8k • 29

ShenaoZ/0.001_ablation_4iters_bs256_dataset

Viewer • Updated Apr 22, 2024 • 51.8k • 35

orpo-explorers/OHP-Stratified-3

Viewer • Updated Apr 22, 2024 • 331k • 31

waadarsh/test-orpo-magnite

Viewer • Updated Apr 22, 2024 • 214 • 30

ShenaoZ/0.001_ablation_5iters_bs256_useresponse_dataset

Viewer • Updated Apr 25, 2024 • 56.9k • 30

ShenaoZ/0.001_4iters_bs256_nodpo_only2third_userresponse_dataset

Viewer • Updated Apr 26, 2024 • 12.2k • 28

ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_dataset

Viewer • Updated Apr 28, 2024 • 62k • 30

YYYYYYibo/ultrafeedback_binarized_phase_2_part_1

Viewer • Updated Apr 28, 2024 • 100 • 33

dmvaldman/showerthought_preferences_full

Viewer • Updated Apr 28, 2024 • 26.1k • 30

kurier-digital/llm_titles_orpo

Viewer • Updated Apr 29, 2024 • 15.2k • 30

nbalepur/Mnemonic_Preferences_ours_with_ties_fixed

Preview • Updated Apr 29, 2024 • 29

ShenaoZ/0.0001_withdpo_4iters_bs256_531lr_dataset

Viewer • Updated Apr 30, 2024 • 51.8k • 31

YYYYYYibo/ultrafeedback_binarized_left_part_3

Viewer • Updated May 1, 2024 • 15k • 29

ShenaoZ/0.001_withdpo_4iters_bs256_432lr_dataset

Viewer • Updated May 1, 2024 • 51.8k • 32

ShenaoZ/0.0001_withdpo_3iters_bs256_551lr_misit_dataset

Viewer • Updated May 4, 2024 • 44.8k • 30

YYYYYYibo/ultrafeedback_binarized_epoch_2_vllm_part_3

Viewer • Updated May 4, 2024 • 5k • 30

YYYYYYibo/ultrafeedback_binarized_rank4_all_minpi_part_2

Viewer • Updated May 4, 2024 • 18.6k • 30

YYYYYYibo/ultrafeedback_binarized_real_rank4_all_train_part_2

Viewer • Updated May 5, 2024 • 18.6k • 29

YYYYYYibo/ultrafeedback_binarized_real_rank4_all_train_part_3

Viewer • Updated May 5, 2024 • 20.5k • 28

StrangeSX/RawdataforAUNQA_TH

Viewer • Updated May 22, 2024 • 2.06k • 41

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part0_mini_3

Viewer • Updated May 6, 2024 • 4.9k • 30

YYYYYYibo/ultrafeedback_binarized_rank4_on_vanilla_part_2

Viewer • Updated May 15, 2024 • 20k • 32

euiyulsong/generated_data_all_cos_500

Viewer • Updated May 18, 2024 • 500 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.30

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.10

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.20

Updated May 20, 2024 • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_1_mini_0

Viewer • Updated May 20, 2024 • 5k • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.40rho0.30

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.40

Updated May 20, 2024 • 29

thewordsmiths/stem_dpo

Viewer • Updated May 31, 2024 • 50k • 29

BahaaEldin0/openai_summarize_comparisons_dataset_with_prompts

Viewer • Updated May 30, 2024 • 260k • 28

iamnguyen/vi-orpo-dpo-mix

Viewer • Updated Jun 3, 2024 • 44.2k • 30

ShenaoZ/SELM-Zephyr-7Bz-dataset

Viewer • Updated Jun 5, 2024 • 51.8k • 30

nhyha/ORPO

Viewer • Updated Jun 12, 2024 • 17 • 38

YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_vllm_part_3_mini_1

Viewer • Updated Jun 17, 2024 • 5.28k • 30

YYYYYYibo/gshf_vllm_1_part_2_mini_7

Viewer • Updated Jul 4, 2024 • 2.5k • 31

YYYYYYibo/gshf_vllm_1_part_2_mini_1

Viewer • Updated Jul 4, 2024 • 2.5k • 29

YYYYYYibo/gshf_vllm_1_part_2_mini_0

Viewer • Updated Jul 4, 2024 • 2.5k • 29

YYYYYYibo/gshf_vllm_1_part_2_mini_5

Viewer • Updated Jul 4, 2024 • 2.5k • 30

YYYYYYibo/gshf_vllm_1_part_2_mini_6

Viewer • Updated Jul 4, 2024 • 2.5k • 29

YYYYYYibo/gshf_vllm_1_part_2_mini_2

Viewer • Updated Jul 4, 2024 • 2.5k • 29

YYYYYYibo/gshf_vllm_1_part_2_mini_3

Viewer • Updated Jul 4, 2024 • 2.5k • 33

YYYYYYibo/gshf_vllm_1_part_2_mini_4

Viewer • Updated Jul 4, 2024 • 2.5k • 30

YYYYYYibo/gshf_vllm_2_part_2_mini_3

Viewer • Updated Jul 5, 2024 • 2.5k • 31

YYYYYYibo/gshf_vllm_2_part_2_mini_1

Viewer • Updated Jul 5, 2024 • 2.5k • 33

YYYYYYibo/gshf_vllm_2_part_2_mini_5

Viewer • Updated Jul 5, 2024 • 2.5k • 28

YYYYYYibo/gshf_vllm_2_part_2_mini_4

Viewer • Updated Jul 5, 2024 • 2.5k • 30

YYYYYYibo/gshf_vllm_2_part_2_mini_6

Viewer • Updated Jul 5, 2024 • 2.5k • 30

YYYYYYibo/gshf_vllm_2_part_2_mini_2

Viewer • Updated Jul 5, 2024 • 2.5k • 32

YYYYYYibo/gshf_vllm_2_part_2_mini_0

Viewer • Updated Jul 5, 2024 • 2.5k • 31

YYYYYYibo/gshf_vllm_2_part_2_mini_7

Viewer • Updated Jul 5, 2024 • 2.5k • 29

YYYYYYibo/gshf_train_part_2_mini_7

Viewer • Updated Jul 5, 2024 • 2.5k • 30

YYYYYYibo/gshf_train_part_2_mini_3

Viewer • Updated Jul 5, 2024 • 2.5k • 30

YYYYYYibo/gshf_train_part_2_mini_6

Viewer • Updated Jul 5, 2024 • 2.5k • 29

YYYYYYibo/gshf_train_part_2_mini_4

Viewer • Updated Jul 5, 2024 • 2.5k • 32

YYYYYYibo/gshf_train_part_2_mini_0

Viewer • Updated Jul 5, 2024 • 2.5k • 35

YYYYYYibo/gshf_train_part_2_mini_1

Viewer • Updated Jul 5, 2024 • 2.5k • 30

YYYYYYibo/gshf_train_part_2_mini_5

Viewer • Updated Jul 5, 2024 • 2.5k • 30

YYYYYYibo/gshf_train_part_2_mini_2

Viewer • Updated Jul 5, 2024 • 2.5k • 31

GokhanAI/Synthetic

Viewer • Updated Nov 13, 2023 • 26.4k • 38 • 1

AlekseyKorshuk/hh-rlhf-pairwise

Viewer • Updated Feb 8, 2023 • 81.4k • 53

AlekseyKorshuk/lmeh-story-cloze-2016

Viewer • Updated May 23, 2023 • 1k • 45

LanXiu/test_dataset

Viewer • Updated Jul 27, 2023 • 768 • 35

mnoukhov/openai_summarize_comparisons_tldrprompt

Viewer • Updated Nov 30, 2023 • 260k • 36

vwxyzjn/cai-conversation-prod-h4

Viewer • Updated Nov 29, 2023 • 169k • 31

vwxyzjn/cai-conversation-dev

Viewer • Updated Jan 9, 2024 • 76 • 38

vwxyzjn/cai-conversation-dev1704834920

Viewer • Updated Jan 9, 2024 • 128 • 31

HuggingFaceH4/grok-conversation-harmless-old

Viewer • Updated Jan 16, 2024 • 44.8k • 48

lamhieu/itorca_dpo_en

Viewer • Updated Jul 1, 2024 • 5.92k • 36 • 1

vwxyzjn/cai-conversation-dev1705620799

Viewer • Updated Jan 18, 2024 • 256 • 32

vwxyzjn/cai-conversation-dev1705628758

Viewer • Updated Jan 19, 2024 • 256 • 44

vwxyzjn/cai-conversation-dev1705632182

Viewer • Updated Jan 19, 2024 • 256 • 43

thangvip/reward-training-data

Viewer • Updated Jan 22, 2024 • 2.97k • 33

Asap7772/ultrafeedback_binarized_relabelled_test

Viewer • Updated Jan 23, 2024 • 32 • 30

diyali95916/ultrafeedback_binarized

Viewer • Updated Jan 25, 2024 • 187k • 32

pvduy/dpo_data_math

Viewer • Updated Jan 30, 2024 • 6.81k • 36

dkshjn/processed_truthy

Viewer • Updated Feb 1, 2024 • 1.02k • 33

weijie210/UFB_prefs_iter_0_pairwise

Viewer • Updated Feb 6, 2024 • 14.7k • 30

vwxyzjn/openhermes-dev__kaist-ai_prometheus-13b-v1.0__1707406405

Viewer • Updated Feb 8, 2024 • 167 • 33

vwxyzjn/ultrafeedback_binarized_1707919621

Viewer • Updated Feb 14, 2024 • 2k • 31

mnoukhov/openai_summarize_generated_20k_relabel_pythia410m-dpo1_margin

Viewer • Updated Feb 22, 2024 • 20k • 32

roleplay4fun/chai-invalid-pairs-ss5-v1.0

Viewer • Updated Feb 27, 2024 • 16.1k • 33

David-Xu/astronomy-stack-dpo

Viewer • Updated Mar 8, 2024 • 19.9k • 51 • 1

quirky-lats-at-mats/NORMAL_BACKDOOR_alpaca_sleeper_agents_toy_safety_v4

Viewer • Updated Mar 11, 2024 • 2.83k • 29

aengusl/noise5_alpaca_sleeper_agents_toy_safety_NOT_TRUNCATED_v4

Viewer • Updated Mar 11, 2024 • 2.83k • 28

vwxyzjn/tldr-preference-trl-style

Viewer • Updated Aug 20, 2024 • 100 • 40

Aditya685/hermes_preference_filtered_data

Viewer • Updated Mar 14, 2024 • 78.4k • 34

Ksgk-fy/alignment-dpo-test03

Viewer • Updated Mar 23, 2024 • 3.78k • 30

ShenaoZhang/0.001_idpo_same_dataset

Viewer • Updated Apr 6, 2024 • 44.8k • 43

ShenaoZhang/0.001_idpo_4iters_ref_response

Viewer • Updated Apr 6, 2024 • 51.8k • 40

mnoukhov/summarize_from_feedback_tldr3_generated_20k_vllm_pythia1b_dpo_temp0.7_length128

Viewer • Updated Apr 14, 2024 • 20k • 36

guoyu-zhang/shp_4

Viewer • Updated Apr 15, 2024 • 1k • 31

guoyu-zhang/usp_3

Viewer • Updated Apr 15, 2024 • 1k • 29

ShenaoZ/0.00001_ablation_dataset

Viewer • Updated Apr 18, 2024 • 44.8k • 30

mnoukhov/summarize_from_feedback_tldr3_labelled_generated_relabel_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 19, 2024 • 9.5k • 35

ShenaoZ/0.001_ablation_declr_4iters_dataset

Viewer • Updated Apr 21, 2024 • 51.8k • 29

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_dpo2_costa_1b_fp16.yml_bfcef

Viewer • Updated Apr 21, 2024 • 107k • 31

orpo-explorers/OHP-Stratified-2

Viewer • Updated Apr 22, 2024 • 331k • 30

ShenaoZ/001_ablation_5iters_bs256_nodpo_dataset

Viewer • Updated Apr 24, 2024 • 58.9k • 44

ShenaoZ/0.001_ablation_4iters_bs256_sample2_dataset

Viewer • Updated Apr 24, 2024 • 51.8k • 35

ShenaoZ/01_ablation_3iters_bs256_nodpo_dataset

Viewer • Updated Apr 24, 2024 • 24.4k • 33

NickyNicky/alexredna_oasst2_dpo_pairs

Viewer • Updated Apr 26, 2024 • 10k • 30

jjmaxwell/llama3_orpo_dpo_clone

Viewer • Updated Apr 28, 2024 • 44.2k • 30

YYYYYYibo/eval-dataset-original

Viewer • Updated May 3, 2024 • 200 • 30

YYYYYYibo/eval-dataset-with-score-merge

Viewer • Updated May 2, 2024 • 200 • 30

YYYYYYibo/ultrafeedback_binarized_plus_minpi_part_3

Viewer • Updated May 3, 2024 • 5k • 29

ShenaoZ/0.001_withdpo_4iters_bs256_5102lr_misit_dataset

Viewer • Updated May 4, 2024 • 19.3k • 28

YYYYYYibo/ultrafeedback_binarized_epoch_2_minpi_part_2

Viewer • Updated May 3, 2024 • 5k • 28

ShenaoZ/0.0_withdpo_4iters_bs256_5102lr_misit_dataset

Viewer • Updated May 4, 2024 • 51.8k • 37

ShenaoZ/0.0001_zephyrgemmasft_withdpo_4iters_bs256_555lr_dataset

Viewer • Updated May 6, 2024 • 51.8k • 35

YYYYYYibo/ultrafeedback_binarized_dataset_offline_part2

Viewer • Updated May 6, 2024 • 20.7k • 32

YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part1_mini_0

Viewer • Updated May 6, 2024 • 4.9k • 32

ShenaoZ/0.01_sft_nodpo_3iters_bs256_531lr_dataset

Viewer • Updated May 7, 2024 • 67.1k • 32

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_2

Viewer • Updated May 8, 2024 • 19.1k • 30

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_vllm_part_3_mini_2

Viewer • Updated May 8, 2024 • 5.08k • 31

YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_3_mini_1

Viewer • Updated May 8, 2024 • 5.18k • 29

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_2_mini_3

Viewer • Updated May 8, 2024 • 5k • 29

ShenaoZ/0.0005_betadpoinit_4iters_bs256_5551lr_dataset

Viewer • Updated May 10, 2024 • 69.1k • 37

Baidicoot/anthropic-helpful-harmless-rlhf

Viewer • Updated May 10, 2024 • 169k • 32

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_pythia410m-dpo-tldr-step873_relabel_pythia1b

Viewer • Updated May 13, 2024 • 20k • 32

yananchen/tp_dpo_pairs_45chosen

Viewer • Updated May 15, 2024 • 3.64k • 30

YYYYYYibo/ultrafeedback_binarized_rank4_on_vanilla_part_1

Viewer • Updated May 15, 2024 • 20k • 31

YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_1_mini_1

Viewer • Updated May 19, 2024 • 5k • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.00

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.10

Updated May 20, 2024 • 30

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.30

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.10

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.10

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.10

Updated May 20, 2024 • 31

mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.30pi0.30

Updated May 20, 2024 • 28

mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.00gamma0.40

Updated May 20, 2024 • 29

mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.40

Updated May 20, 2024 • 29

YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_2_mini_0

Viewer • Updated May 20, 2024 • 5k • 35

GENIAC-Team-Ozaki/tuninig-dataset_pref_20pct_full-sft-finetuned-stage4-iter86000

Viewer • Updated May 22, 2024 • 20.3k • 29

BahaaEldin0/small_dataset_with_rewards

Viewer • Updated May 30, 2024 • 1k • 31

BahaaEldin0/updated_dataset_with_prompts

Viewer • Updated Oct 2, 2024 • 1k • 37

stojchet/test_disc_ds

Viewer • Updated Jun 7, 2024 • 20 • 32

thepowerfuldeez/Qwen-summarize-dataset-test

Viewer • Updated Jun 17, 2024 • 187 • 30

Marjovl/berkeley-nest-Nectar-DPO

Viewer • Updated Jun 19, 2024 • 1.1M • 57 • 1

nlee-208/UF1000-eurus

Viewer • Updated Jul 1, 2024 • 1k • 30

heli-stand/hh-rlhf-harmless-base-trl-style

Viewer • Updated Jul 3, 2024 • 44.8k • 3.16k • 1

YYYYYYibo/full_simple_online_vllm_part_2_mini_1

Viewer • Updated Jul 4, 2024 • 2.5k • 33

YYYYYYibo/full_simple_online_vllm_part_2_mini_7

Viewer • Updated Jul 4, 2024 • 2.3k • 30

YYYYYYibo/full_simple_online_vllm_part_2_mini_6

Viewer • Updated Jul 4, 2024 • 2.3k • 29

YYYYYYibo/full_simple_online_vllm_part_2_mini_5

Viewer • Updated Jul 4, 2024 • 2.1k • 30

YYYYYYibo/full_simple_online_vllm_part_2_mini_0

Viewer • Updated Jul 4, 2024 • 2.5k • 31

YYYYYYibo/full_simple_online_vllm_part_2_mini_3

Viewer • Updated Jul 4, 2024 • 2.5k • 29

YYYYYYibo/full_simple_online_vllm_part_2_mini_4

Viewer • Updated Jul 4, 2024 • 2.3k • 29

YYYYYYibo/full_simple_online_vllm_part_2_mini_2

Viewer • Updated Jul 4, 2024 • 2.5k • 29

YYYYYYibo/full_simple_online_train_part_2_mini_6

Viewer • Updated Jul 4, 2024 • 2.38k • 31

YYYYYYibo/full_simple_online_train_part_2_mini_7

Viewer • Updated Jul 4, 2024 • 2.38k • 30

YYYYYYibo/full_simple_online_train_part_2_mini_0

Viewer • Updated Jul 4, 2024 • 2.38k • 30

YYYYYYibo/full_simple_online_train_part_2_mini_2

Viewer • Updated Jul 4, 2024 • 2.38k • 30

YYYYYYibo/full_simple_online_train_part_2_mini_3

Viewer • Updated Jul 4, 2024 • 2.38k • 30

YYYYYYibo/full_simple_online_train_part_2_mini_4

Viewer • Updated Jul 4, 2024 • 2.38k • 31

YYYYYYibo/full_simple_online_train_part_2_mini_1

Viewer • Updated Jul 4, 2024 • 2.38k • 29

YYYYYYibo/full_simple_online_train_part_2_mini_5

Viewer • Updated Jul 4, 2024 • 2.38k • 28

YYYYYYibo/full_simple_online_vllm_part_3_mini_1

Viewer • Updated Jul 4, 2024 • 2.44k • 34

YYYYYYibo/full_simple_online_vllm_part_3_mini_6

Viewer • Updated Jul 4, 2024 • 2.54k • 31

YYYYYYibo/full_simple_online_vllm_part_3_mini_0

Viewer • Updated Jul 4, 2024 • 2.34k • 32

YYYYYYibo/full_simple_online_vllm_part_3_mini_5

Viewer • Updated Jul 4, 2024 • 2.04k • 28

YYYYYYibo/full_simple_online_vllm_part_3_mini_3

Viewer • Updated Jul 4, 2024 • 2.64k • 28

YYYYYYibo/full_simple_online_vllm_part_3_mini_2

Viewer • Updated Jul 4, 2024 • 2.64k • 31

YYYYYYibo/full_simple_online_vllm_part_3_mini_7

Viewer • Updated Jul 4, 2024 • 2.25k • 31

YYYYYYibo/full_simple_online_vllm_part_3_mini_4

Viewer • Updated Jul 4, 2024 • 2.44k • 32

YYYYYYibo/full_simple_online_train_part_3_mini_0

Viewer • Updated Jul 4, 2024 • 2.42k • 30

YYYYYYibo/full_simple_online_train_part_3_mini_6

Viewer • Updated Jul 4, 2024 • 2.42k • 29

YYYYYYibo/full_simple_online_train_part_3_mini_1

Viewer • Updated Jul 4, 2024 • 2.42k • 30

YYYYYYibo/full_simple_online_train_part_3_mini_7

Viewer • Updated Jul 4, 2024 • 2.42k • 30

YYYYYYibo/full_simple_online_train_part_3_mini_3

Viewer • Updated Jul 4, 2024 • 2.42k • 29

YYYYYYibo/full_simple_online_train_part_3_mini_2

Viewer • Updated Jul 4, 2024 • 2.42k • 30

YYYYYYibo/full_simple_online_train_part_3_mini_5

Viewer • Updated Jul 4, 2024 • 2.42k • 30

YYYYYYibo/full_simple_online_train_part_3_mini_4

Viewer • Updated Jul 4, 2024 • 2.42k • 27

YYYYYYibo/gshf_vllm_1_part_3_mini_0

Viewer • Updated Jul 5, 2024 • 2.64k • 30

YYYYYYibo/gshf_vllm_1_part_3_mini_2

Viewer • Updated Jul 5, 2024 • 2.64k • 32

YYYYYYibo/gshf_vllm_1_part_3_mini_6

Viewer • Updated Jul 5, 2024 • 2.64k • 31

YYYYYYibo/gshf_vllm_1_part_3_mini_5

Viewer • Updated Jul 5, 2024 • 2.64k • 30

YYYYYYibo/gshf_vllm_1_part_3_mini_1

Viewer • Updated Jul 5, 2024 • 2.64k • 32

YYYYYYibo/gshf_vllm_1_part_3_mini_3

Viewer • Updated Jul 5, 2024 • 2.64k • 30

YYYYYYibo/gshf_vllm_1_part_3_mini_7

Viewer • Updated Jul 5, 2024 • 2.65k • 30

YYYYYYibo/gshf_vllm_1_part_3_mini_4

Viewer • Updated Jul 5, 2024 • 2.64k • 31

YYYYYYibo/gshf_vllm_2_part_3_mini_2

Viewer • Updated Jul 5, 2024 • 2.64k • 29

YYYYYYibo/gshf_vllm_2_part_3_mini_1

Viewer • Updated Jul 5, 2024 • 2.64k • 29

YYYYYYibo/gshf_vllm_2_part_3_mini_6

Viewer • Updated Jul 5, 2024 • 2.64k • 31

YYYYYYibo/gshf_vllm_2_part_3_mini_5

Viewer • Updated Jul 5, 2024 • 2.64k • 31

YYYYYYibo/gshf_vllm_2_part_3_mini_0

Viewer • Updated Jul 5, 2024 • 2.64k • 29

YYYYYYibo/gshf_vllm_2_part_3_mini_3

Viewer • Updated Jul 5, 2024 • 2.64k • 31

YYYYYYibo/gshf_vllm_2_part_3_mini_7

Viewer • Updated Jul 5, 2024 • 2.65k • 29

YYYYYYibo/gshf_vllm_2_part_3_mini_4

Viewer • Updated Jul 5, 2024 • 2.64k • 31

YYYYYYibo/gshf_train_part_3_mini_0

Viewer • Updated Jul 5, 2024 • 2.64k • 29

YYYYYYibo/gshf_train_part_3_mini_1

Viewer • Updated Jul 5, 2024 • 2.64k • 34

YYYYYYibo/gshf_train_part_3_mini_6

Viewer • Updated Jul 5, 2024 • 2.64k • 32

YYYYYYibo/gshf_train_part_3_mini_3

Viewer • Updated Jul 5, 2024 • 2.64k • 32

YYYYYYibo/gshf_train_part_3_mini_5

Viewer • Updated Jul 5, 2024 • 2.64k • 30

YYYYYYibo/gshf_train_part_3_mini_2

Viewer • Updated Jul 5, 2024 • 2.64k • 31

YYYYYYibo/gshf_train_part_3_mini_4

Viewer • Updated Jul 5, 2024 • 2.64k • 30

YYYYYYibo/gshf_train_part_3_mini_7

Viewer • Updated Jul 5, 2024 • 2.65k • 32

liswei/rm-static-zhTW

Viewer • Updated May 19, 2023 • 81.4k • 39 • 30

pvduy/hh_shp_oa_gpt4_rm_dataset_vicuna_format

Updated Apr 28, 2023 • 29 • 1

mii-llm/enex-dpo

Viewer • Updated Jan 16, 2024 • 2.99k • 29 • 1

AlekseyKorshuk/combined-pairwise

Viewer • Updated Feb 8, 2023 • 222k • 29

pvduy/hh_shp_oa_gpt4_rm_dataset_vicuna_formatoa

Updated May 1, 2023 • 30

amazingvince/full-dpo

Viewer • Updated Nov 30, 2023 • 186k • 28

mii-llm/cult-dpo

Viewer • Updated Jan 17, 2024 • 987 • 29

winglian/cortex-dumpster-fire-gemma-v5-crashed

Updated Mar 6, 2024 • 28

August4293/Self_Alignment_Preference-Dataset

Viewer • Updated Mar 18, 2024 • 4.45k • 32

Joyqiuyue/lima_preference_dataset

Viewer • Updated Apr 9, 2024 • 50 • 30

gagan3012/oasis

Viewer • Updated Apr 9, 2024 • 2.34M • 29

theblackhacker/arc_dpo

Viewer • Updated Apr 9, 2024 • 38.6k • 29

Dhananjayg22/legal-dpo

Viewer • Updated Apr 18, 2024 • 300 • 30

ShenaoZ/0.001_3iters_bs256_declr_nodpo_dataset

Viewer • Updated Apr 26, 2024 • 44.8k • 29

ShenaoZ/0.01_withdpo_4iters_bs256_531lr_dataset

Viewer • Updated May 7, 2024 • 51.8k • 47

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_0

Viewer • Updated May 9, 2024 • 4.85k • 29

crumb/semantic-corruption-t5-v1_1-small

Viewer • Updated May 21, 2024 • 2.28k • 32

crumb/semantic-corruption-t5-v1_1-base

Viewer • Updated May 21, 2024 • 1.54k • 30

crumb/semantic-corruption-t5-v1_1-large

Viewer • Updated May 21, 2024 • 753 • 30

mnlp-nsoai/dpo-student-preferences

Viewer • Updated May 21, 2024 • 18.4k • 28

ContextualAI/ultrabin_clean_max_chosen_rand_rejected_rationalized

Viewer • Updated Jun 12, 2024 • 60.9k • 36

malteos/translation_test

Viewer • Updated Jun 12, 2024 • 10 • 31

malteos/translation_test2

Viewer • Updated Jun 18, 2024 • 50 • 31

nayohan/contextual-dpo-v0.1-ko

Viewer • Updated Jun 30, 2024 • 1.37k • 30

nayohan/reward-bench-ko

Viewer • Updated Jun 30, 2024 • 8.11k • 58

Windy/tmp_output_apc

Viewer • Updated Jun 30, 2024 • 60 • 31

Windy/tmp_output_apc_t1

Viewer • Updated Jul 1, 2024 • 60 • 31

Windy/tmp_output_apc_t1_noshort

Viewer • Updated Jul 1, 2024 • 60 • 29

sert121/preference_data_mapped_v8

Viewer • Updated Jul 1, 2024 • 960 • 28

sert121/preference_data_mapped_v7

Viewer • Updated Jul 1, 2024 • 3.2k • 31

Windy/tmp_output_ultr4_t0

Viewer • Updated Jul 3, 2024 • 60 • 30

Windy/tmp_output_ultr4_t0_top1

Viewer • Updated Jul 3, 2024 • 60 • 31

August4293/gsm8k_preference_dataset_it_1

Viewer • Updated Jul 4, 2024 • 895 • 27

August4293/gsm8k_preference_dataset_it_2

Viewer • Updated Jul 4, 2024 • 379 • 31

Windy/tmp_output_ultr4_t1

Viewer • Updated Jul 4, 2024 • 60 • 31

Columbia-NLP/DPO-distilabel-capybara-dpo-7k-binarized

Viewer • Updated Jul 10, 2024 • 7.56k • 33

Columbia-NLP/DPO-distilabel-intel-orca-dpo-pairs_cleaned

Viewer • Updated Jul 10, 2024 • 12.8k • 39

Columbia-NLP/DPO-UltraFeedback_binarized

Viewer • Updated Jul 10, 2024 • 62.7k • 38

Columbia-NLP/DPO-py-dpo-v0.1

Viewer • Updated Jul 10, 2024 • 9.47k • 30

Columbia-NLP/DPO-tldr-summarisation-preferences

Viewer • Updated Jul 10, 2024 • 177k • 38

Columbia-NLP/DPO-PKU-SafeRLHF

Viewer • Updated Jul 10, 2024 • 136k • 34

Columbia-NLP/DPO-Nectar

Viewer • Updated Jul 10, 2024 • 183k • 33

Columbia-NLP/DPO-hh-rlhf

Viewer • Updated Jul 10, 2024 • 169k • 36

Windy/tmp_output_lima_t0

Viewer • Updated Jul 6, 2024 • 60 • 30

Windy/tmp_output_ultr4_t1_fromsimpt0_rankerthresh4

Viewer • Updated Jul 7, 2024 • 60 • 29

YYYYYYibo/test_vllm_mini_0

Viewer • Updated Jul 8, 2024 • 2.5k • 30

Windy/tmp_output_ultraw_t0

Viewer • Updated Jul 8, 2024 • 60 • 33

Windy/tmp_output_ultr4_t1_simthresh03

Viewer • Updated Jul 8, 2024 • 60 • 30

Windy/tmp_output_ultr4_t1_simthresh03_rank6

Viewer • Updated Jul 9, 2024 • 60 • 33

flydust/ultrafeedback-labeled

Viewer • Updated Jul 9, 2024 • 61.8k • 33

YYYYYYibo/test_get_pi

Viewer • Updated Jul 9, 2024 • 1k • 32

YYYYYYibo/test_pairrm

Viewer • Updated Jul 9, 2024 • 21.1k • 32

sert121/preference_data_v11_cleaned_filtered

Viewer • Updated Jul 10, 2024 • 3.55k • 28

sert121/preference_data_v10_cleaned_filtered

Viewer • Updated Jul 10, 2024 • 2.38k • 29

Windy/ultr4_v3_t1_trlsft_mv1

Viewer • Updated Jul 10, 2024 • 99 • 30

Xalphinions/llama3_ultrafeedback_with_tie

Viewer • Updated Jul 10, 2024 • 61.8k • 29

Windy/ultr4_v3_t1_trlsft_mv1_ranksim

Viewer • Updated Jul 10, 2024 • 7.11k • 31

Xalphinions/UltraFeedback_with_tie

Viewer • Updated Jul 10, 2024 • 133k • 28

nlee-208/UF-Mistral-Self101

Viewer • Updated Jul 10, 2024 • 2.5k • 33

Windy/ultr4_v3_t1_trlsft_mv1_ranksim_top1

Viewer • Updated Jul 10, 2024 • 15k • 31