mradermacher/syrian_qwen_3.5_2B-GGUF
Same weights, converted vs theBOrg32/syrian_qwen_3.5_2B. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 18 new tensors.
Tensors changed: Norms 0/61, Embeddings 0/1, MLP 0/72, Attention 0/24
Same weights, converted vs theBOrg32/syrian_qwen_3.5_2B. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 18 new tensors.
Tensors changed: Norms 0/61, Embeddings 0/1, MLP 0/72, Attention 0/24