unsloth/DeepSeek-R1-Distill-Qwen-14B
Same weights, repacked vs deepseek-ai/DeepSeek-R1-Distill-Qwen-14B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Attention 0/336, MLP 0/144, Norms 0/97, lm_head 0/1
6 derivatives checked
- mlx-community/Unsloth-DeepSeek-R1-Distill-Qwen-14B-4bit: Quantization
- Gorilla4X/Quacken-R1-14B-FP8: Same weights, converted
- doodums/DeepSeek-R1-Distill-Qwen-14B-Q4_K_M-GGUF: Quantization
- mathdong01/DeepSeek-R1-14B-Finetuned: LoRA-style
- Samarth2511/DS-14B-DA-full-both-r32: LoRA-style
- Samarth2511/DS-14B-Prefs-r32-full: LoRA-style
2 other repos hold byte-for-byte identical weight files.