mradermacher/Firefly-v4-Beta-2-GGUF
Same weights, converted (fewer layers) vs Guilherme34/Firefly-v4-Beta-2. mradermacher/Firefly-v4-Beta-2-GGUF matches part of Guilherme34/Firefly-v4-Beta-2 (565 of its 2011 tensors; the rest of Guilherme34/Firefly-v4-Beta-2 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 36 new tensors.
Tensors changed: Embeddings 0/2, Norms 0/247, MLP 0/105, other 0/71, Attention 0/140