mradermacher/Qwen2.5-Omni-3B-GGUF
Same weights, converted vs Qwen/Qwen2.5-Omni-3B. Same weights stored in another dtype (BF16/F32 → F16/F32).
Tensors changed: Norms 0/38, MLP 0/57, Attention 0/133, lm_head 0/1
Same weights, converted vs Qwen/Qwen2.5-Omni-3B. Same weights stored in another dtype (BF16/F32 → F16/F32).
Tensors changed: Norms 0/38, MLP 0/57, Attention 0/133, lm_head 0/1