mradermacher/syrian_qwen_3.5_4B-GGUF
Same weights, converted vs theBOrg32/syrian_qwen_3.5_4B. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 24 new tensors.
Tensors changed: Norms 0/81, Embeddings 0/1, MLP 0/96, Attention 0/32
Same weights, converted vs theBOrg32/syrian_qwen_3.5_4B. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 24 new tensors.
Tensors changed: Norms 0/81, Embeddings 0/1, MLP 0/96, Attention 0/32