oopere/pruned10-llama-3.2-3B
Same weights, converted vs meta-llama/Llama-3.2-3B. Same weights stored in another dtype (BF16 → F16).
Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112
Same weights, converted vs meta-llama/Llama-3.2-3B. Same weights stored in another dtype (BF16 → F16).
Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112