ClaudioItaly/Intelligence-7

Partial fine-tune vs ATH-MaaS/Marco-o1. Partial change: 80% of the weights changed (attention, mlp, norms), in 26 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 50/57, MLP 78/84, Attention 182/196, lm_head 0/1

2 derivatives checked

• mradermacher/Intelligence-7-i1-GGUF: Quantization
• mradermacher/Intelligence-7-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse