baconnier/Napoleon-3.5-12B

Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 64% of the weights changed (attention, mlp, norms), in 31 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 84/208, Attention 196/332, Norms 94/215

2 derivatives checked

• mradermacher/Napoleon-3.5-12B-i1-GGUF: Quantization
• mradermacher/Napoleon-3.5-12B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse