The sleeepeer/Llama-3.1-8B-Instruct-GRPO-alpaca-combine-100-no-KL-42 galaxy

2 models are built on sleeepeer/Llama-3.1-8B-Instruct-GRPO-alpaca-combine-100-no-KL-42: 0 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 31 times in the last 30 days.

Most downloaded direct derivatives

• sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-AT-1 (finetune), 12 downloads in 30 days
• sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-1 (finetune), 11 downloads in 30 days

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