bartowski/Nemomix-v0.1-12B-GGUF
Same weights, converted vs MarinaraSpaghetti/Nemomix-v1.0-12B. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160
Same weights, converted vs MarinaraSpaghetti/Nemomix-v1.0-12B. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160