mradermacher/Tessera-1B-Nano-Base-GGUF
Same weights, converted vs yava-code/Tessera-1B-Nano-Base. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128
Same weights, converted vs yava-code/Tessera-1B-Nano-Base. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128