mradermacher/loopl-vl-4b-GGUF

Same weights, converted (fewer layers) vs cagataydev/loopl-vl-4b. mradermacher/loopl-vl-4b-GGUF matches part of cagataydev/loopl-vl-4b (398 of its 713 tensors; the rest of cagataydev/loopl-vl-4b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse