ClaudioItaly/Intelligence-Cod-Rag-7B

Partial fine-tune vs ATH-MaaS/Marco-o1. Partial change: 78% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 2/57, MLP 69/84, Attention 104/196, lm_head 1/1

2 derivatives checked

• mradermacher/Intelligence-Cod-Rag-7B-i1-GGUF: Full fine-tune
• mradermacher/Intelligence-Cod-Rag-7B-GGUF: Partial fine-tune

On the Hub · Downloads on Model Pulse