ClaudioItaly/Intelligence-Cod-Rag-7B-V2

Partial fine-tune vs ATH-MaaS/Marco-o1. Partial change: 23% of the weights changed (attention, mlp, norms), in 24 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 2/57, MLP 22/84, Attention 32/196, lm_head 0/1

2 derivatives checked

• mradermacher/Intelligence-Cod-Rag-7B-V2-i1-GGUF: Quantization
• mradermacher/Intelligence-Cod-Rag-7B-V2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse