exdysa/NousCoder-14B-Q4_K_M-layers
Full fine-tune (fewer layers) vs Qwen/Qwen3-14B. exdysa/NousCoder-14B-Q4_K_M-layers matches part of Qwen/Qwen3-14B (11 of its 443 tensors; the rest of Qwen/Qwen3-14B has no counterpart). On the shared part: exdysa/NousCoder-14B-Q4_K_M-layers is a GGUF (Q4_K/Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 1 of 1 layers.
Tensors changed: Norms 2/4, MLP 3/3, Attention 4/4