mradermacher/Light-IF-14B-i1-GGUF
Full fine-tune vs qihoo360/Light-IF-14B. mradermacher/Light-IF-14B-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 110/161, MLP 120/120, Attention 160/160, Embeddings 1/1, lm_head 1/1