Jackrong/Qwopus3.5-4B-v3-MTP-GGUF
Same weights, converted vs Jackrong/Qwopus3.5-4B-v3. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 39 new tensors.
Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/81, Attention 0/32
Same weights, converted vs Jackrong/Qwopus3.5-4B-v3. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 39 new tensors.
Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/81, Attention 0/32