48 lines
1.1 KiB
Markdown
48 lines
1.1 KiB
Markdown
---
|
|
language: id
|
|
tags:
|
|
- aurum-brain-ai
|
|
- indonesian
|
|
- coding
|
|
- fine-tuned
|
|
- qwen
|
|
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
# 🧠 Aurum Brain AI
|
|
|
|
Custom fine-tuned model dari Qwen2.5-1.5B-Instruct untuk Bahasa Indonesia, coding, dan percakapan pintar.
|
|
|
|
## Spesifikasi
|
|
- Base: Qwen/Qwen2.5-1.5B-Instruct
|
|
- Fine-tune: LoRA r=16, alpha=32
|
|
- Bahasa: Indonesia (native)
|
|
- Format: PyTorch (safetensors)
|
|
|
|
## Kemampuan
|
|
- 🇮🇩 Bahasa Indonesia natural
|
|
- 💻 Coding expert (Python, JS, Rust, Go, SQL, dll)
|
|
- 🌐 Web Development (HTML, CSS, React, Next.js)
|
|
- 🧠 Problem Solving & debugging
|
|
- 🤖 Agent AI capabilities
|
|
|
|
## Cara Pakai via HF Inference API
|
|
|
|
```python
|
|
from huggingface_hub import InferenceClient
|
|
|
|
client = InferenceClient(model="arissuga/aurum-brain-ai")
|
|
response = client.text_generation(
|
|
"Halo, siapa kamu?",
|
|
max_new_tokens=100,
|
|
)
|
|
print(response)
|
|
```
|
|
|
|
## System Prompt
|
|
Lihat file `system_prompt.txt` di repo ini untuk personality AI.
|
|
|
|
## Training
|
|
Auto-trained 8x/hari via GitHub Actions. Dataset: 68+ percakapan Bahasa Indonesia.
|