The EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO galaxy

6 models are built on EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO: 5 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 2,834 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-i1-GGUF (quantized), 1.1K downloads in 30 days
• mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF (quantized), 265 downloads in 30 days
• EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V3-ORPO (finetune), 16 downloads in 30 days

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