mradermacher/Infinite-Sumika-9B-GGUF
Same weights, converted vs ABX-AI/Infinite-Sumika-9B. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: MLP 0/120, Norms 0/81, Attention 0/160, Embeddings 0/1, lm_head 0/1
Same weights, converted vs ABX-AI/Infinite-Sumika-9B. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: MLP 0/120, Norms 0/81, Attention 0/160, Embeddings 0/1, lm_head 0/1