zerofata/G4-MeroMero-v2-31B-GGUF

Same weights, converted (fewer layers) vs zerofata/G4-MeroMero-v2-31B. zerofata/G4-MeroMero-v2-31B-GGUF matches part of zerofata/G4-MeroMero-v2-31B (772 of its 1188 tensors; the rest of zerofata/G4-MeroMero-v2-31B 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

On the Hub · Downloads on Model Pulse