mradermacher/Qwen2.5-3B-Smart-GGUF
Same weights, converted vs bunnycore/Qwen2.5-3B-Smart. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252
Same weights, converted vs bunnycore/Qwen2.5-3B-Smart. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252