timm/qwen3_vit_306m.qwen3_5_2b
Same weights, converted vs Qwen/Qwen3.5-2B. Same weights stored in another dtype (BF16/F32 → F32), plus 97 new tensors.
Tensors changed: Attention 0/96, Norms 0/96, Embeddings 0/1
Same weights, converted vs Qwen/Qwen3.5-2B. Same weights stored in another dtype (BF16/F32 → F32), plus 97 new tensors.
Tensors changed: Attention 0/96, Norms 0/96, Embeddings 0/1