mradermacher/Capybara-Finnish-V1-8B-GGUF
Same weights, converted vs mpasila/Capybara-Finnish-V1-8B. Same weights stored in another dtype (F16 → F16/F32), plus 3 new tensors.
Tensors changed: Norms 0/130, MLP 0/128, Attention 0/64, Embeddings 0/1
Same weights, converted vs mpasila/Capybara-Finnish-V1-8B. Same weights stored in another dtype (F16 → F16/F32), plus 3 new tensors.
Tensors changed: Norms 0/130, MLP 0/128, Attention 0/64, Embeddings 0/1