Tiiny/SmallThinker-4BA0.6B-Instruct-INT4-QAT
Full fine-tune vs Tiiny/SmallThinker-4BA0.6B-Instruct. Tiiny/SmallThinker-4BA0.6B-Instruct-INT4-QAT is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, other 32/32, Norms 65/65, Attention 128/128, lm_head 1/1