allenai/tulu-2.5-preference-data download history
allenai/tulu-2.5-preference-data is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,367 times (87 in the last 7 days), and 30,075 times in total. It ranks #15,275 among datasets by monthly downloads.
Tulu 2.5 Preference Data This dataset contains the preference dataset splits used to train the models described in Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback. We cleaned and formatted all datasets to be in the same format. This means some
Models trained on tulu-2.5-preference-data
55 models list it as training data.
- mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-i1-GGUF 1.3K downloads in 30 days
- mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-i1-GGUF 1.2K downloads in 30 days
- mradermacher/llama-3-tulu-v2.5-8b-uf-mean-8b-uf-rm-i1-GGUF 1K downloads in 30 days
- allenai/tulu-v2.5-13b-uf-rm 832 downloads in 30 days
- allenai/llama-3-tulu-2-8b-uf-mean-rm 476 downloads in 30 days
- mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-GGUF 441 downloads in 30 days
- mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF 431 downloads in 30 days
- mradermacher/llama-3-tulu-v2.5-8b-uf-mean-8b-uf-rm-GGUF 348 downloads in 30 days
- allenai/tulu-v2.5-ppo-13b-uf-mean 259 downloads in 30 days
- allenai/tulu-v2.5-dpo-13b-stackexchange-60k 165 downloads in 30 days
- allenai/tulu-v2.5-ppo-13b-chatbot-arena-2023 142 downloads in 30 days
- allenai/tulu-v2.5-dpo-13b-hh-rlhf 140 downloads in 30 days