mradermacher/bloomz-1b7-GGUF
Same weights, converted vs bigscience/bloomz-1b7. Same weights stored in another dtype (F16 → F16/F32), plus 1 new tensors.
Tensors changed: Norms 0/98, MLP 0/96, Attention 0/48, Embeddings 0/3
Same weights, converted vs bigscience/bloomz-1b7. Same weights stored in another dtype (F16 → F16/F32), plus 1 new tensors.
Tensors changed: Norms 0/98, MLP 0/96, Attention 0/48, Embeddings 0/3