alkindivv/
Llama-3.2-1B-Indo:latest

6 2 weeks ago

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct that has been optimized for Indonesian language understanding and generation. The fine-tuning process utilized Low-Rank Adaptation (LoRA) to efficiently adapt the model while minimizi

... /
params
2685ded66166 · 85B
{
"num_ctx": 4096,
"num_thread": 12,
"repeat_penalty": 1.12,
"temperature": 0.2,
"top_p": 0.9
}