The EpistemeAI/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO galaxy

14 models are built on EpistemeAI/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO: 10 quantized, 4 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 3,981 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-i1-GGUF (quantized), 668 downloads in 30 days
• mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-GGUF (quantized), 477 downloads in 30 days
• EpistemeAI/ReasoningCore-3B-T1_1 (finetune), 24 downloads in 30 days
• EpistemeAI/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align (finetune), 8 downloads in 30 days

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