interpretable-finetuning/qwen2.5-1.5b-unaliased
Same weights, repacked vs Qwen/Qwen2.5-1.5B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196
Same weights, repacked vs Qwen/Qwen2.5-1.5B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196