Nexesenex/Llama_3.2_3b_SmartiPantz_0.21

Full fine-tune vs MaziyarPanahi/calme-3.3-llamaloi-3b. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: MLP 84/84, Embeddings 1/1, Norms 0/57, Attention 112/112

1 derivatives checked

• mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse