mradermacher/inferencevision-pythia-1B-GGUF
Same weights, converted vs doguilmak/inferencevision-pythia-1B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/2, Norms 0/66, Attention 0/32, MLP 0/64
Same weights, converted vs doguilmak/inferencevision-pythia-1B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/2, Norms 0/66, Attention 0/32, MLP 0/64