martimfasantos/EuroLLM-1.7B-Instruct-SimPO
Partial fine-tune vs utter-project/EuroLLM-1.7B-Instruct. Partial change: 84% of the weights changed (attention, lm_head, mlp, norms), in 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 9/49, MLP 72/72, Attention 96/96
1 derivatives checked
- mradermacher/EuroLLM-1.7B-Instruct-SimPO-GGUF: Same weights, converted