alignment-handbook/zephyr-7b-dpo-full download history
alignment-handbook/zephyr-7b-dpo-full is a 7.2B-parameter text generation model by alignment-handbook. In the last 30 days it was downloaded 127 times (26 in the last 7 days), and 10,858 times in total.
It ranks #161,704 on the Hub by monthly downloads and #42,866 among text generation models.
It has 3 likes.
It is a fine-tune of alignment-handbook/zephyr-7b-sft-full.
7 models build on zephyr-7b-dpo-full: 4 quantized, 2 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 634 times in the last 30 days. See the zephyr-7b-dpo-full galaxy.
Most downloaded derivatives
- mradermacher/zephyr-7b-dpo-full-GGUF (quantized), 261 downloads in 30 days
- mradermacher/zephyr-7b-dpo-full-i1-GGUF (quantized), 206 downloads in 30 days
- tensorblock/zephyr-7b-dpo-full-GGUF (quantized), 20 downloads in 30 days
- youndukn/zephyr-7b-sft-lora-romantic (finetune), 10 downloads in 30 days
- paultimothymooney/zephyr-7b-dpo-full-Q8_0-GGUF (quantized), 5 downloads in 30 days
- youndukn/zephyr-7b-sft-lora (finetune), 4 downloads in 30 days
- youndukn/zephyr-7b-sft-lora-check (adapter), 1 downloads in 30 days
Open alignment-handbook/zephyr-7b-dpo-full on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.