README.md

---
library_name: transformers
license: mit
datasets:
- kodetr/stunting-qa-v1
language:
- id
metrics:
- bleu
- glue
- rouge
base_model:
- meta-llama/Llama-3.2-3B-Instruct
pipeline_tag: text-generation
---

### Model Description

<!-- Provide a longer summary of what this model is. -->

Konsultasi(Q&A) stunting pada anak

- **Developed by:** Tanwir
- **Language :** Indonesia

### Training

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d6d2f8b06abf924b24349d/6QshLUs9eAnsKJZOGP2jc.png)

### Information Result Training

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d6d2f8b06abf924b24349d/eHj9f-z3ZkLrtwvBcMzy-.png)

### Evaluation (GLUE)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d6d2f8b06abf924b24349d/obTYsbLRg9gD2_8rzN8G5.png)

### Evaluation (ROUGE)

- **ROUGE Base Model:** {'rouge1': 0.32442426784015754, 'rouge2': 0.21091087320145585, 'rougeL': 0.2997913044723025, 'rougeLsum': 0.3028164031975752}
- **ROUGE Finetuned Model:** {'rouge1': 0.45885281015363844, 'rouge2': 0.33303682535111623, 'rougeL': 0.42486098123248783, 'rougeLsum': 0.43147191004805796}

### BERTSCORE

- **BERTScore Base Model - F1:** 0.7268
- **BERTScore Finetuned Model - F1:** 0.7687

### Use with transformers

Pastikan untuk memperbarui instalasi transformer Anda melalui pip install --upgrade transformer.

```python
import torch
from transformers import pipeline

model_id = "kodetr/stunting-qa-v3"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "Jelaskan definisi 1000 hari pertama kehidupan."},
    {"role": "user", "content": "Apa itu 1000 hari pertama kehidupan?"},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```