mradermacher/Vikhr-2-VL-2b-Instruct-experimental-GGUF

Same weights, converted (fewer layers) vs Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental. mradermacher/Vikhr-2-VL-2b-Instruct-experimental-GGUF matches part of Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental (338 of its 729 tensors; the rest of Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196

On the Hub · Downloads on Model Pulse