EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO
3 derivatives checked
- mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-i1-GGUF: Quantization
- mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF: Same weights, converted
- EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V3-ORPO: LoRA-style