artificialguybr/LLAMA3.2-1B-Synthia-I-Redmond
Full fine-tune vs NousResearch/Llama-3.2-1B. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Norms 9/33, MLP 48/48, Attention 64/64
3 derivatives checked
- mradermacher/LLAMA3.2-1B-Synthia-I-Redmond-i1-GGUF: Quantization
- artificialguybr/LLAMA3.2-1B-Synthia-I-Redmond-gguf: Same weights, converted
- mradermacher/LLAMA3.2-1B-Synthia-I-Redmond-GGUF: Same weights, converted