mradermacher/smallprint-4b-GGUF

Same weights, converted (fewer layers) vs Peter-A-P/smallprint-4b. mradermacher/smallprint-4b-GGUF matches part of Peter-A-P/smallprint-4b (623 of its 2076 tensors; the rest of Peter-A-P/smallprint-4b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132

On the Hub · Downloads on Model Pulse