powermove72/Llama-NextGenmix-4b
Partial fine-tune vs bunnycore/Llama-3.2-3B-Mix. Partial change: 67% of the weights changed (attention, embeddings, mlp, norms), in 28 of 28 layers.
Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 32/57, MLP 60/84, Attention 76/112
1 derivatives checked
- mradermacher/Llama-NextGenmix-4b-GGUF: Same weights, converted