trl-lib/Qwen2-0.5B-OnlineDPO download history

trl-lib/Qwen2-0.5B-OnlineDPO is a 494M-parameter text generation model by trl-lib. In the last 30 days it was downloaded 26 times (6 in the last 7 days), and 315 times in total.

It ranks #342,391 on the Hub by monthly downloads and #96,463 among text generation models.

It has 1 likes.

It is a fine-tune of Qwen/Qwen2-0.5B-Instruct.

1 models build on Qwen2-0.5B-OnlineDPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 480 times in the last 30 days. See the Qwen2-0.5B-OnlineDPO galaxy.

Most downloaded derivatives

Open trl-lib/Qwen2-0.5B-OnlineDPO on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.