The Muadil/Llama-3.2-1B-Instruct_sum_PPO_Skywork_20.0k_1_1ep galaxy

1 models are built on Muadil/Llama-3.2-1B-Instruct_sum_PPO_Skywork_20.0k_1_1ep: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 550 times in the last 30 days.

Most downloaded direct derivatives

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