MaziyarPanahi/calme-3.3-llamaloi-3b
Full fine-tune vs meta-llama/Llama-3.2-3B. 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
6 derivatives checked
- MaziyarPanahi/calme-3.3-llamaloi-3b-GGUF: Same weights, converted
- mradermacher/calme-3.3-llamaloi-3b-GGUF: Same weights, converted
- ysn-rfd/calme-3.3-llamaloi-3b-GGUF: Quantization
- Nexesenex/Llama_3.2_3b_Kermes_v2: Full fine-tune
- Nexesenex/Llama_3.2_3b_Kermes_0.20: Full fine-tune
- Nexesenex/Llama_3.2_3b_SmartiPantz_0.21: Full fine-tune