jwest33/qwen3-vl-8b-instruct-null-space-abliterated-GGUF
Full fine-tune (fewer layers) vs Qwen/Qwen3-VL-8B-Instruct. jwest33/qwen3-vl-8b-instruct-null-space-abliterated-GGUF matches part of Qwen/Qwen3-VL-8B-Instruct (399 of its 750 tensors; the rest of Qwen/Qwen3-VL-8B-Instruct has no counterpart). On the shared part: jwest33/qwen3-vl-8b-instruct-null-space-abliterated-GGUF is a GGUF (F16) of different weights. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144, lm_head 1/1