giux78/buddy-nesso-sft-v1
Full fine-tune vs mii-llm/nesso-0.4B-agentic. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 47/65, MLP 96/96, Attention 128/128
1 derivatives checked
- mradermacher/buddy-nesso-sft-v1-GGUF: Same weights, converted