mradermacher/occitan-gemma-3-4b-it-dora-GGUF

Same weights, converted (fewer layers) vs julienp79/occitan-gemma-3-4b-it-dora. mradermacher/occitan-gemma-3-4b-it-dora-GGUF matches part of julienp79/occitan-gemma-3-4b-it-dora (444 of its 883 tensors; the rest of julienp79/occitan-gemma-3-4b-it-dora has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse