DevQuasar/falcon2-11B-GGUF
Same weights, converted vs tiiuae/falcon-11B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/122, MLP 0/120, Attention 0/60, Embeddings 0/1, lm_head 0/1
Same weights, converted vs tiiuae/falcon-11B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/122, MLP 0/120, Attention 0/60, Embeddings 0/1, lm_head 0/1