unsloth/Qwen2.5-3B
Same weights, repacked vs Qwen/Qwen2.5-3B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252
4 derivatives checked
- phuocsang/qwen2.5-3B-Vietnamese-Law: Adapter
- tensorblock/Qwen2.5-3B-GGUF: Quantization
- tanquangduong/Qwen2.5-3B-Instruct-TinyStories: LoRA-style
- tanquangduong/Qwen2.5-3B-DPO-TinyStories: LoRA-style
7 other repos hold byte-for-byte identical weight files.