sparkle-reasoning/SparkleRL-7B-Stage1 download history
sparkle-reasoning/SparkleRL-7B-Stage1 is a 7.6B-parameter reinforcement learning model by sparkle-reasoning. In the last 30 days it was downloaded 24 times (9 in the last 7 days), and 27,575 times in total.
It ranks #360,952 on the Hub by monthly downloads and #6,688 among reinforcement learning models.
It has 2 likes.
3 models build on SparkleRL-7B-Stage1: 3 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 1,359 times in the last 30 days. See the SparkleRL-7B-Stage1 galaxy.
Most downloaded derivatives
- mradermacher/es-qwen-math-base-7b-3k-40k-ds_o2-stage1-step2000-i1-GGUF (quantized), 844 downloads in 30 days
- mradermacher/es-qwen-math-base-7b-3k-40k-ds_o2-stage1-step2000-GGUF (quantized), 333 downloads in 30 days
- mradermacher/SparkleRL-7B-Stage1-GGUF (quantized), 158 downloads in 30 days
Open sparkle-reasoning/SparkleRL-7B-Stage1 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.