bartowski/Ateron_Gemma-4-Novelist-Eclipse-31B-GGUF

Same weights, converted (fewer layers) vs Ateron/Gemma-4-Novelist-Eclipse-31B. bartowski/Ateron_Gemma-4-Novelist-Eclipse-31B-GGUF matches part of Ateron/Gemma-4-Novelist-Eclipse-31B (773 of its 1189 tensors; the rest of Ateron/Gemma-4-Novelist-Eclipse-31B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32), plus 61 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230, lm_head 0/1

On the Hub · Downloads on Model Pulse