SergeyLizin/GigaChat3.1-10B-A1.8B-GGUF
Full fine-tune vs ai-sage/GigaChat3-10B-A1.8B-base. SergeyLizin/GigaChat3.1-10B-A1.8B-GGUF is a GGUF (BF16) of different weights. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 79/79, MLP 103/103, Attention 78/78