dfap/qwen2.5-coder-continue
Full fine-tune vs unsloth/Qwen2.5-Coder-0.5B. dfap/qwen2.5-coder-continue is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 168/168