Weyaxi/Einstein-v8-Llama3.2-1B
Full fine-tune vs meta-llama/Llama-3.2-1B. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Norms 30/33, MLP 48/48, Attention 64/64
3 derivatives checked
- mradermacher/Einstein-v8-Llama3.2-1B-i1-GGUF: Quantization
- mradermacher/Einstein-v8-Llama3.2-1B-GGUF: Same weights, converted
- Novaciano/Sapo-3.2-1B: Full fine-tune