MasterControlAIML/DeepSeek-R1-Qwen2.5-3b-LLM-Judge-Reward-JSON-Unstructured-To-Structured-Lora-gguf
Not comparable yet vs unsloth/Qwen2.5-3B-Instruct. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 434/339 match), usually an architecture llama.cpp's name map doesn't cover yet.