Nexesenex/Llama_3.2_3b_SmartiHatz_0.1b

Full fine-tune vs SaisExperiments/Evil-Alpaca-3B-L3.2. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

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

2 derivatives checked

• mradermacher/Llama_3.2_3b_SmartiHatz_0.1b_bf16-i1-GGUF: Quantization
• mradermacher/Llama_3.2_3b_SmartiHatz_0.1b_bf16-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse