mradermacher/Supertron-VL-4B-GGUF

Same weights, converted (fewer layers) vs Surpem/Supertron-VL-4B. mradermacher/Supertron-VL-4B-GGUF matches part of Surpem/Supertron-VL-4B (398 of its 713 tensors; the rest of Surpem/Supertron-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