ertghiu256/deepseek-r1-0528-distilled-qwen3
Same weights, repacked vs Qwen/Qwen3-4B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144
2 derivatives checked
- ertghiu256/deepseek-r1-0528-distilled-qwen3-gguf: Quantization
- ertghiu256/qwen-3-reasoning-combination-with-deepseek: LoRA-style
22 other repos hold byte-for-byte identical weight files.