mradermacher/TrueSkin-VL-2B-GGUF

Same weights, converted (fewer layers) vs mrbeniwal/TrueSkin-VL-2B. mradermacher/TrueSkin-VL-2B-GGUF matches part of mrbeniwal/TrueSkin-VL-2B (338 of its 729 tensors; the rest of mrbeniwal/TrueSkin-VL-2B has no counterpart). On the shared part: Same weights stored in another dtype (F16/BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse