prithivMLmods/dots.mocr-GGUF

Same weights, converted (fewer layers) vs dots-studio/dots.mocr. prithivMLmods/dots.mocr-GGUF matches part of dots-studio/dots.mocr (339 of its 643 tensors; the rest of dots-studio/dots.mocr has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse