dthryjdrk/Qwen2.5-VL-7B-Instruct-abliterated-Q8_0-GGUF
Quantization (fewer layers) vs huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated. dthryjdrk/Qwen2.5-VL-7B-Instruct-abliterated-Q8_0-GGUF matches part of huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated (339 of its 729 tensors; the rest of huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated has no counterpart). On the shared part: dthryjdrk/Qwen2.5-VL-7B-Instruct-abliterated-Q8_0-GGUF is a GGUF quantization (Q8_0) of the same weights: 141 tensors match exactly and 198 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1