oriental-lab/Tr-Jp-LLM-1.5B
Full fine-tune vs SakanaAI/TinySwallow-1.5B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 37/57, MLP 84/84, Attention 191/196
1 derivatives checked
- mradermacher/Tr-Jp-LLM-1.5B-GGUF: Same weights, converted