Dahoas/full-hh-rlhf download history
Dahoas/full-hh-rlhf is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 415 times (77 in the last 7 days), and 266,024 times in total. It ranks #38,289 among datasets by monthly downloads.
Dataset Card for "full-hh-rlhf" Anthropic's HH dataset reformatted into prompt, chosen, rejected samples.
Models trained on full-hh-rlhf
34 models list it as training data.
- mradermacher/stablelm-tuned-alpha-7b-i1-GGUF 4.4K downloads in 30 days
- mradermacher/stablelm-tuned-alpha-7b-GGUF 1.7K downloads in 30 days
- stabilityai/stablelm-tuned-alpha-3b 1.4K downloads in 30 days
- stabilityai/stablelm-tuned-alpha-7b 984 downloads in 30 days
- mradermacher/stablelm-tuned-alpha-3b-16bit-i1-GGUF 831 downloads in 30 days
- mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF 425 downloads in 30 days
- mradermacher/stablelm-tuned-alpha-3b-16bit-GGUF 421 downloads in 30 days
- rl-bandits-lab/hhrlhf_rm 204 downloads in 30 days
- keyfan/bloomz-rlhf 90 downloads in 30 days
- AdamG012/chat-opt-350m-reward-deepspeed 63 downloads in 30 days
- AdamG012/chat-opt-1.3b-rlhf-critic-deepspeed 46 downloads in 30 days
- vvsotnikov/stablelm-tuned-alpha-3b-16bit 46 downloads in 30 days