darrellbest/Qwen3.5-4B-Heretic-GGUF
Same weights, converted vs darrellbest/Qwen3.5-4B-Heretic. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 39 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32
Same weights, converted vs darrellbest/Qwen3.5-4B-Heretic. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 39 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32