mradermacher/Qwen-SEA-LION-v4-4B-VL-Magic_decensored-GGUF
Same weights, converted (fewer layers) vs MagicalAlchemist/Qwen-SEA-LION-v4-4B-VL-Magic_decensored. mradermacher/Qwen-SEA-LION-v4-4B-VL-Magic_decensored-GGUF matches part of MagicalAlchemist/Qwen-SEA-LION-v4-4B-VL-Magic_decensored (398 of its 713 tensors; the rest of MagicalAlchemist/Qwen-SEA-LION-v4-4B-VL-Magic_decensored has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144