GusssElion/cinder-0.5b
Full fine-tune vs Qwen/Qwen2-0.5B. GusssElion/cinder-0.5b is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 29/49, MLP 72/72, Attention 168/168