electricpipelines/Qwen3-4B-GGUF
Full fine-tune vs Qwen/Qwen3-4B. electricpipelines/Qwen3-4B-GGUF is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 72/145, MLP 108/108, Attention 144/144