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
f7f4d7cbfd33 · 62B
{
"stop": [
"User:",
"Assistant:"
],
"temperature": 0.7,
"top_p": 0.9
}