AdversarialRLHF on Hugging Face: downloads and rankings
AdversarialRLHF has 21 tracked models, downloaded 313 times in the last 30 days and 1,198 times in total; 43 datasets, downloaded 696 times in the last 30 days. AdversarialRLHF Wrapped: the last 12 months.
Models by downloads in the last 30 days
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata 84 downloads, model
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_propsft_propprefix_nokl 40 downloads, model
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_allprefixsft_prefix 32 downloads, model
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl 20 downloads, model
- AdversarialRLHF/pythia410m-sft-tldr-propprefix 15 downloads, text generation
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix 15 downloads, model
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl 14 downloads, model
- AdversarialRLHF/pythia410m-sft-tldr 11 downloads, text generation
- AdversarialRLHF/pythia410m-sft-tldr-allprefix 10 downloads, text generation
- AdversarialRLHF/ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_propprefix 10 downloads, model
- AdversarialRLHF/pythia410m-rm-tldr6.9b 10 downloads, text classification
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_kl0.005 8 downloads, model
- AdversarialRLHF/pythia410m-rm-tldr6.9b_randomizeprefix 7 downloads, text classification
- AdversarialRLHF/ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl 7 downloads, model
- AdversarialRLHF/pythia410m-rm-tldr6.9b_logprobcondboth 7 downloads, text classification
- AdversarialRLHF/pythia410m-rm-tldr6.9b_logprobcondpropallprefix 7 downloads, text classification
- AdversarialRLHF/pythia410m-rm-tldr6.9b_logprobcondallprefix 4 downloads, text classification
- AdversarialRLHF/pythia410m-rm-tldr6.9b_logprobcondprefix 4 downloads, text classification
- AdversarialRLHF/pythia410m-rm-tldr6.9b_logprobcondsuffix 3 downloads, text classification
- AdversarialRLHF/pythia410m-rm-tldr6.9b_prefix_in_chosen 3 downloads, text classification
- AdversarialRLHF/pythia410m-rm-tldr6.9b_logprobcondpropprefix 2 downloads, text classification
Datasets by downloads in the last 30 days
- AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_relabel_pythia6.9b_logprobs 60 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_prefix_chosen 56 downloads
- AdversarialRLHF/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144_propprefix 51 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieallprefix 39 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojiepropallprefix 27 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieboth 27 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojiesuffix 23 downloads
- AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_relabel_pythia6.9b_3emojieprefix_chosen 21 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieprefix 20 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_checkpoint-104_eval-dataset 18 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_3emojieprefix_randomize 18 downloads
- AdversarialRLHF/ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl_full_eval-dataset 16 downloads
- AdversarialRLHF/410M-sft-tldr-eval-dataset 15 downloads
- AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_trained_allprefix 15 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_eval-dataset 15 downloads
- AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft 14 downloads
- AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojiepropprefix 14 downloads
- AdversarialRLHF/pythia410m-sft-tldr-allprefix_eval-dataset 13 downloads
- AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_relabel_pythia6.9b 13 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl_checkpoint-78_eval-dataset 13 downloads
- AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_trained 12 downloads
- AdversarialRLHF/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144_allprefix 11 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl_checkpoint-78_eval-dataset 11 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_kl0.005_52_eval-dataset 11 downloads
- AdversarialRLHF/ppo_pythia410m_tldr6.9b_rm410mdata_eval-dataset 11 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl_checkpoint-255_eval-dataset 11 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_eval-dataset 11 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl_checkpoint-104_eval-dataset 11 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_checkpoint-26_eval-dataset 11 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl_checkpoint-52_eval-dataset 10 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl_checkpoint-104_eval-dataset 9 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_checkpoint-255_eval-dataset 9 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_checkpoint-52_eval-dataset 8 downloads
- AdversarialRLHF/sft_pythia410m_tldr_prefix_0.25_eval-dataset 8 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl_eval-dataset 8 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl_checkpoint-52_eval-dataset 8 downloads
- AdversarialRLHF/pythia410m-sft-tldr-propprefix_eval-dataset 7 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl_checkpoint-26_eval-dataset 7 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl_checkpoint-26_eval-dataset 7 downloads
- AdversarialRLHF/ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_propprefix_eval-dataset 7 downloads
- AdversarialRLHF/generations_ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl_eval-dataset 7 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl_checkpoint-184_eval-dataset 7 downloads
- AdversarialRLHF/rloo_pythia410m_tldr6.9b_rm410mdata_mergedsft0.3_prefix_nokl_checkpoint-255_eval-dataset 6 downloads
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.