sail/Llama-3.2-3B-Oat-Zero
Full fine-tune vs lkevinzc/Llama-3.2-3B-NuminaQA. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 22/57, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/Llama-3.2-3B-Oat-Zero-i1-GGUF: Quantization
- mradermacher/Llama-3.2-3B-Oat-Zero-GGUF: Same weights, converted