mradermacher/Revisual-R1-final-GGUF

Same weights, converted (fewer layers) vs csfufu/Revisual-R1-final. mradermacher/Revisual-R1-final-GGUF matches part of csfufu/Revisual-R1-final (339 of its 729 tensors; the rest of csfufu/Revisual-R1-final has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse