kaeru39's picture

kaeru39 PRO

ryota39

·

AI & ML interests

LLM × RL

Recent Activity

updated a model about 21 hours ago

cyberagent/ca-reward-3b-ja

liked a model 3 days ago

openai/gpt-oss-20b

updated a collection 4 days ago

catlm-reward-v0.1

View all activity

Organizations

ryota39 's datasets 35

ryota39/llmjp-chatbot-arena-v2

Viewer • Updated 29 days ago • 594 • 249

ryota39/aya-ja-evol-inst

Viewer • Updated May 21 • 29.1k • 2

ryota39/llm-jp-chatbot-arena-conversations-reformatted

Viewer • Updated May 19 • 990 • 21 • 1

ryota39/reviews_and_summaries2

Viewer • Updated Apr 26 • 50 • 7

ryota39/reviews_and_summaries

Viewer • Updated Apr 26 • 50 • 18

ryota39/movie_reviews_local

Viewer • Updated Apr 26 • 50 • 4

ryota39/movie_reviews

Viewer • Updated Apr 26 • 50 • 5

ryota39/wild_chat_ja

Viewer • Updated Jan 23 • 3.49k • 2

ryota39/aya-evol-instruct

Viewer • Updated Jan 6 • 29.2k • 4

ryota39/JCommonsenseMorality

Viewer • Updated Nov 29, 2024 • 9.98k • 9

ryota39/hh-rlhf

Viewer • Updated Nov 26, 2024 • 169k • 7

ryota39/preference-en-ja-100k

Viewer • Updated Nov 19, 2024 • 101k • 19 • 1

ryota39/preference_test

Viewer • Updated Nov 16, 2024 • 29.6k • 5

ryota39/preference_test_annotated

Viewer • Updated Nov 10, 2024 • 5 • 4

ryota39/open_preference_v0.4

Viewer • Updated Aug 26, 2024 • 202k • 6 • 1

ryota39/webgpt_comparisons-ja

Viewer • Updated Aug 16, 2024 • 17.4k • 9 • 1

ryota39/synthetic-instruct-gptj-pairwise-ja

Viewer • Updated Aug 16, 2024 • 33.1k • 10 • 1

ryota39/self-rewarding_instruct_AIFT_M3_scored

Viewer • Updated Jul 28, 2024 • 7.11k • 10

ryota39/self-rewarding_instruct_AIFT_M2_scored

Viewer • Updated Jul 28, 2024 • 7k • 5

ryota39/self-rewarding_instruct_AIFT_M1_scored

Viewer • Updated Jul 27, 2024 • 4k • 9

ryota39/Synthetic-JP-Conversations-Magpie-Nemotron-4-10k_scored

Viewer • Updated Jul 25, 2024 • 10.1k • 7

ryota39/aya_ja_evol

Viewer • Updated Jul 16, 2024 • 31.3k • 6

ryota39/hh-rlhf-12k-ja_orpo

Viewer • Updated Jul 4, 2024 • 12k • 14 • 1

ryota39/izumi-lab-dpo-45k

Viewer • Updated Jul 4, 2024 • 45.7k • 7 • 1

ryota39/open_preference-v0.3

Viewer • Updated Jul 4, 2024 • 58.4k • 3

ryota39/open_preference_v0.2

Viewer • Updated Jul 4, 2024 • 98.5k • 16

ryota39/open_preference_v0.1

Viewer • Updated Jun 25, 2024 • 49.2k • 14

ryota39/dpo-ja-45k

Viewer • Updated Jun 15, 2024 • 45.2k • 9

ryota39/dpo-49k

Viewer • Updated Jun 15, 2024 • 49.2k • 12

ryota39/janli_synthetic_rationale

Viewer • Updated Jun 12, 2024 • 14.4k • 3 • 1