9 repos
HuggingFaceH4/summarize_from_feedback
No description
3
3 commits
HuggingFaceH4/h4-tests-format-dpo-dataset
0
2 commits
HuggingFaceH4/orca_dpo_pairs_no_system_prompt
4
Dahoas/static-hh
Static split of Anthropic's Helpful Harmless dataset. Contains base-online and rejection sampled…
21
11 commits
HuggingFaceH4/testing_h4
Dataset Card for "testing_h4"
10 commits
HuggingFaceH4/hh-rlhf-h4
Dataset Card for "hh-rlhf-h4"
7
13 commits
HuggingFaceH4/test-dataset-all-splits
Dataset Card for "test-dataset-all-splits"
1
8 commits
We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs
HuggingFaceH4/OpenHermes-2.5-preferences-v0-deduped
2