ericflo/Llama-3.2-3B-COT
Partial fine-tune vs meta-llama/Llama-3.2-3B. Partial change: 88% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 13/57, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/Llama-3.2-3B-COT-i1-GGUF: Quantization
- mradermacher/Llama-3.2-3B-COT-GGUF: Same weights, converted