The alphaXiv/evidence-multi-rlm-sft-4b galaxy

1 models are built on alphaXiv/evidence-multi-rlm-sft-4b: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 37 times in the last 30 days.

Most downloaded direct derivatives

• alphaXiv/evidence-multi-rlm-4b-grpo-step100 (finetune), 9 downloads in 30 days

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