trl-internal-testing/descriptiveness-sentiment-trl-style download history
trl-internal-testing/descriptiveness-sentiment-trl-style is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,121 times (420 in the last 7 days), and 58,191 times in total. It ranks #17,728 among datasets by monthly downloads.
TRL's Sentiment and Descriptiveness Preference Dataset The dataset comes from https://arxiv.org/abs/1909.08593, one of the earliest RLHF work from OpenAI. We preprocess the dataset using our standard prompt, chosen, rejected format. Reproduce this dataset Download the descript
Models trained on descriptiveness-sentiment-trl-style
18 models list it as training data.
- mradermacher/FedPPO-Confused-Pythia-70M-a0-GGUF 356 downloads in 30 days
- mradermacher/FedPPO-Isolated-Pythia-70M-a1-GGUF 346 downloads in 30 days
- mradermacher/FedPPO-Pythia-70M-a1-GGUF 329 downloads in 30 days
- mradermacher/FedPPO-Isolated-Pythia-70M-a0-GGUF 293 downloads in 30 days
- mradermacher/FedPPO-Collaborative-Pythia-70M-a1-GGUF 272 downloads in 30 days
- mradermacher/FedPPO-Pythia-70M-a0-GGUF 258 downloads in 30 days
- mradermacher/FedPPO-Collaborative-Pythia-70M-a0-GGUF 212 downloads in 30 days
- mradermacher/FedPPO-Confused-Pythia-70M-a1-GGUF 210 downloads in 30 days
- bikalnetomi/RLHF-PPO-PPOModel-LLama3-1B-v1.0 21 downloads in 30 days
- bikalnetomi/RLHF-PPO-PPOModel-LLama3-1B-v1.3 20 downloads in 30 days
- nileshmalpeddi/ppo 20 downloads in 30 days
- bikalnetomi/RLHF-PPO-PPOModel-LLama3-1B-v1.1 19 downloads in 30 days
Open trl-internal-testing/descriptiveness-sentiment-trl-style on Hugging Face