arun11karthik/cellsense-fim-0.5b
Full fine-tune vs Qwen/Qwen2.5-Coder-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 12/49, MLP 72/72, Attention 161/168
1 derivatives checked
- mradermacher/cellsense-fim-0.5b-GGUF: Same weights, converted