ReDiX/Artemide-3.5
Partial fine-tune vs microsoft/Phi-3.5-mini-instruct. Partial change: 32% of the weights changed (attention, embeddings, lm_head, mlp), in 22 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 18/64, Attention 18/64, lm_head 1/1
1 derivatives checked
- mradermacher/Artemide-3.5-i1-GGUF: Quantization