davidxifeng/Confucius4-R2T2-gguf
Same weights, converted vs netease-youdao/Confucius4-R2T2. Same weights stored in another dtype (BF16 → F16).
Tensors changed: other 0/11, MLP 0/180, Norms 0/211, Attention 0/304, Embeddings 0/1
Same weights, converted vs netease-youdao/Confucius4-R2T2. Same weights stored in another dtype (BF16 → F16).
Tensors changed: other 0/11, MLP 0/180, Norms 0/211, Attention 0/304, Embeddings 0/1