abaryan/GRPO_GSM8K_Qwen2.5-1.5B_NoQuantisation download history

abaryan/GRPO_GSM8K_Qwen2.5-1.5B_NoQuantisation is a 1.5B-parameter reinforcement learning model by abaryan. In the last 30 days it was downloaded 11 times (7 in the last 7 days), and 26 times in total.

It ranks #731,830 on the Hub by monthly downloads and #14,004 among reinforcement learning models.

It has 0 likes.

It is a fine-tune of Qwen/Qwen2.5-1.5B-Instruct.

Open abaryan/GRPO_GSM8K_Qwen2.5-1.5B_NoQuantisation on Hugging Face