qingy2024/GRMR-V3-L3B
Full fine-tune vs unsloth/Llama-3.2-3B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 15/57, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/GRMR-V3-L3B-GGUF: Same weights, converted
- qingy2024/GRMR-V3-L3B-GGUF: Same weights, converted