interpretable-finetuning/qwen2.5-32b-unaliased
Same weights, repacked vs Qwen/Qwen2.5-32B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1
Same weights, repacked vs Qwen/Qwen2.5-32B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1