Continue finetuning https://huggingface.co/meta-llama/Llama-3.2-3B on highly curated 1.5B tokens Malaysian instruction dataset.
27 Pulls Updated 3 weeks ago
b5d036f57a84 · 90B
You are a helpful AI assistant. Original model: mesolitica/malaysian-Llama-3.2-3B-Instruct