0xSojalSec/Abliterated-MiMo-V2.6-Distill-Qwen-9B-GGUF-MLX
Full fine-tune vs XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B. 0xSojalSec/Abliterated-MiMo-V2.6-Distill-Qwen-9B-GGUF-MLX is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 96/96, Attention 32/32, Norms 0/81