Downloads · 30 days
13
4% of all-time downloads
qrizan/indonesian-medical-qwen2.5-1.5b
indonesian-medical-qwen2.5-1.5b is a machine learning model from qrizan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Model Qwen2.5-1.5B-Instruct yang di-fine-tune untuk menjawab pertanyaan kesehatan umum dalam Bahasa Indonesia. Output selalu berformat JSON terstruktur dengan field jawaban dan disclaimer.
Downloads · 30 days
13
4% of all-time downloads
All-time downloads
319
Public
Parameters
1.5B
6.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.1 GB · 99%
From the Hugging Face model README
Model Qwen2.5-1.5B-Instruct yang di-fine-tune untuk menjawab pertanyaan kesehatan umum
dalam Bahasa Indonesia. Output selalu berformat JSON terstruktur dengan field jawaban
dan disclaimer.
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch, json
model_id = "qrizan/indonesian-medical-qwen2.5-1.5b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
model.eval()
system = (
"Kamu adalah asisten kesehatan berbahasa Indonesia. "
"Jawab pertanyaan medis umum dengan bahasa sederhana. "
"Selalu sertakan disclaimer untuk konsultasi ke dokter."
)
question = "Apa gejala umum diabetes tipe 2?"
prompt = (
f"<|im_start|>system
{system}<|im_end|>
"
f"<|im_start|>user
{question}<|im_end|>
"
f"<|im_start|>assistant
"
)
inp = tokenizer(prompt, return_tensors="pt").to(model.device)
input_len = inp["input_ids"].shape[1]
with torch.no_grad():
out = model.generate(**inp, max_new_tokens=220, do_sample=False, pad_token_id=tokenizer.pad_token_id)
result = tokenizer.decode(out[0][input_len:], skip_special_tokens=True).strip()
print(json.loads(result))
# Output: {"jawaban": "...", "disclaimer": "..."}
{
"baseline_format_metrics": {
"total": 50,
"json_valid_pct": 0.0,
"has_jawaban_pct": 0.0,
"has_disclaimer_pct": 0.0,
"disclaimer_has_dokter_pct": 0.0,
"overall_format_compliance_pct": 0.0
},
"finetuned_format_metrics": {
"total": 50,
"json_valid_pct": 96.0,
"has_jawaban_pct": 96.0,
"has_disclaimer_pct": 96.0,
"disclaimer_has_dokter_pct": 96.0,
"overall_format_compliance_pct": 96.0
},
"gpt4o_mini_format_metrics": {
"total": 50,
"json_valid_pct": 100.0,
"has_jawaban_pct": 98.0,
"has_disclaimer_pct": 100.0,
"disclaimer_has_dokter_pct": 100.0,
"overall_format_compliance_pct": 98.0
},
"perplexity": {
"baseline": 3.031702656866234,
"fine_tuned": 2.00000459098804
},
"llm_judge_avg_scores": {
"baseline": {
"akurasi_informasi": 3.1,
"kejelasan_bahasa": 3.7,
"kelengkapan_disclaimer": 1.5,
"konsistensi_format": 2.25
},
"fine_tuned": {
"akurasi_informasi": 4.25,
"kejelasan_bahasa": 4.65,
"kelengkapan_disclaimer": 4.8,
"konsistensi_format": 3.95
},
"gpt4o_mini": {
"akurasi_informasi": 4.65,
"kejelasan_bahasa": 4.8,
"kelengkapan_disclaimer": 4.8,
"konsistensi_format": 4.25
}
}
}