41 lines
923 B
Markdown
41 lines
923 B
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- id
|
||
|
|
license: mit
|
||
|
|
tags:
|
||
|
|
- indonesian
|
||
|
|
- gpt2
|
||
|
|
- question-answering
|
||
|
|
- text-generation
|
||
|
|
datasets:
|
||
|
|
- wikipedia
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# Masa AI - Q&A (150M Parameters)
|
||
|
|
|
||
|
|
Model bahasa Indonesia yang di-fine-tune untuk menjawab pertanyaan sederhana.
|
||
|
|
|
||
|
|
## Cara Penggunaan
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import GPT2LMHeadModel, AutoTokenizer
|
||
|
|
|
||
|
|
model = GPT2LMHeadModel.from_pretrained("yasmeenimron/masa-ai-qa")
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained("yasmeenimron/masa-ai-qa")
|
||
|
|
|
||
|
|
prompt = "Pertanyaan: Apa ibu kota Indonesia?\nJawaban:"
|
||
|
|
inputs = tokenizer(prompt, return_tensors="pt")
|
||
|
|
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
|
||
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||
|
|
```
|
||
|
|
|
||
|
|
## Base Model
|
||
|
|
|
||
|
|
Model ini di-fine-tune dari [yasmeenimron/masa-ai](https://huggingface.co/yasmeenimron/masa-ai)
|
||
|
|
|
||
|
|
## License
|
||
|
|
|
||
|
|
MIT License
|