jan-hq/Deepseek-Qwen2.5-7B-Redistil-GRPO download history

jan-hq/Deepseek-Qwen2.5-7B-Redistil-GRPO is a 7.6B-parameter text generation model by jan-hq. In the last 30 days it was downloaded 22 times (11 in the last 7 days), and 58 times in total.

It ranks #383,731 on the Hub by monthly downloads and #112,357 among text generation models.

It has 0 likes.

It is a fine-tune of jan-hq/Deepseek-Qwen2.5-7B-Redistil.

1 models build on Deepseek-Qwen2.5-7B-Redistil-GRPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 172 times in the last 30 days. See the Deepseek-Qwen2.5-7B-Redistil-GRPO galaxy.

Most downloaded derivatives

• mradermacher/Deepseek-Qwen2.5-7B-Redistil-GRPO-GGUF (quantized), 150 downloads in 30 days

Open jan-hq/Deepseek-Qwen2.5-7B-Redistil-GRPO on Hugging Face