ClaudioItaly/Intelligence-Cod-Rag-7B-v4

Full fine-tune vs ATH-MaaS/Marco-o1. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1

2 derivatives checked

• mradermacher/Intelligence-Cod-Rag-7B-v4-GGUF: Same weights, converted
• ClaudioItaly/King-7B: Partial fine-tune

On the Hub · Downloads on Model Pulse