xuanwulab/HaS_Text_0209_0.6B_Q8
Full fine-tune vs Qwen/Qwen3-0.6B. xuanwulab/HaS_Text_0209_0.6B_Q8 is a GGUF (Q8_0/F32) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 106/113, MLP 84/84, Attention 112/112