rohanjain2312/grpo-reward-hacking-fixed-kl-qwen05b download history

rohanjain2312/grpo-reward-hacking-fixed-kl-qwen05b is a 494M-parameter text generation model by rohanjain2312. In the last 30 days it was downloaded 570 times (47 in the last 7 days), and 570 times in total.

It ranks #64,939 on the Hub by monthly downloads and #15,500 among text generation models.

It has 0 likes.

It is a fine-tune of Qwen/Qwen2.5-0.5B-Instruct.

Open rohanjain2312/grpo-reward-hacking-fixed-kl-qwen05b on Hugging Face