pthinc/Cicikus-v3-1.4B
Partial fine-tune vs meta-llama/Llama-3.2-1B. Partial change: 79% of the weights changed (attention, mlp, norms), in 16 of 16 layers.
Tensors changed: Embeddings 0/1, Norms 16/33, MLP 48/48, Attention 64/64
2 derivatives checked
- mradermacher/Cicikus-v3-1.4B-i1-GGUF: Quantization
- mradermacher/Cicikus-v3-1.4B-GGUF: LoRA-style