ClaudioItaly/intelligence-cod-rag-7b-v3.1

Partial fine-tune vs ATH-MaaS/Marco-o1. Partial change: 75% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 6/57, MLP 66/84, Attention 96/196, lm_head 1/1

2 derivatives checked

• mradermacher/intelligence-cod-rag-7b-v3.1-i1-GGUF: Quantization
• mradermacher/intelligence-cod-rag-7b-v3.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse