bhismaperkasa/gemma-3-270M-it-chat-seru-adapter

📱 Gemma 3 270M Form Generator - LoRA Adapter

LoRA adapter untuk generate form definitions dalam JSON format. Trained dengan Unsloth framework untuk efficiency maksimal.

🎯 Model Info

• Base Model: google/gemma-3-270m-it
• Training: Unsloth + BF16 pure (no quantization)
• LoRA Rank: 128
• Dataset: bhismaperkasa/form_dinamis
• Language: Bahasa Indonesia
• Epochs: 4
• Size: ~50 MB (adapter only)

🚀 Usage

Load Adapter

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-3-270m-it",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Load adapter
model = PeftModel.from_pretrained(
    base_model,
    "bhismaperkasa/gemma-3-270M-it-chat-seru-adapter"
)
model.eval()

tokenizer = AutoTokenizer.from_pretrained("bhismaperkasa/gemma-3-270M-it-chat-seru-adapter")

Generate Form

prompt = "<start_of_turn>user\nbuatkan form login<end_of_turn>\n<start_of_turn>model\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result.split("<start_of_turn>model\n")[-1])

📊 Training Details

• Framework: Unsloth (2x faster, 60% less VRAM)
• Precision: BF16 (pure, no quantization)
• Batch Size: 8
• Learning Rate: 5e-5
• Optimizer: AdamW 8-bit
• Final Loss: ~0.23-0.25

🎓 Why LoRA Adapter?

Using adapter instead of merged model because:

• ✅ Smaller size (~50 MB vs ~540 MB)
• ✅ Easy to switch base models
• ✅ Better for experimentation
• ✅ Can combine multiple adapters

🔗 Related Models

• Merged Version: bhismaperkasa/gemma-3-270m-form-generator-bf16 (if available)

⚖️ License

Apache 2.0 (following Gemma license)