mmp2055/Qwen2.5-VL-3B-uncensored-bughunter-v9
Quantization (fewer layers) vs huihui-ai/Qwen2.5-VL-3B-Instruct-abliterated. mmp2055/Qwen2.5-VL-3B-uncensored-bughunter-v9 matches part of huihui-ai/Qwen2.5-VL-3B-Instruct-abliterated (434 of its 824 tensors; the rest of huihui-ai/Qwen2.5-VL-3B-Instruct-abliterated has no counterpart). On the shared part: mmp2055/Qwen2.5-VL-3B-uncensored-bughunter-v9 is a GGUF quantization (Q4_K_M) of the same weights: 181 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252