Thai reasoning model that shows its step-by-step thinking — beats DeepSeek R1 70B and Typhoon R1 70B on Thai benchmarks (avg 71.58 vs 63.31/65.42) at half their size. ~24 GB RAM.
{
"num_ctx": 32768,
"num_predict": 16384,
"stop": [
"<｜User｜>",
"<｜Assistant｜>",
"<｜end▁of▁sentence｜>"
],
"temperature": 0.6,
"top_k": 40,
"top_p": 0.95
}