manifestasi/smolVLM-161M-q4-manifestasi

This Model is for Educational Research Purpose Only.

Sample Code

%%capture
!pip install -U bitsandbytes

from transformers import AutoProcessor, AutoModelForVision2Seq
import torch
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

processor = AutoProcessor.from_pretrained("manifestasi/smolVLM-161M-q4-manifestasi")
model = AutoModelForVision2Seq.from_pretrained("manifestasi/smolVLM-161M-q4-manifestasi",
                                                torch_dtype=torch.float16,
                                                _attn_implementation="eager").to(DEVICE)

from PIL import Image
from transformers.image_utils import load_image


# Load images
# image1 = load_image("https://huggingface.co/spaces/HuggingFaceTB/SmolVLM/resolve/main/example_images/rococo.jpg")
image2 = load_image("/kaggle/input/bandaraaa/799269_1200.jpg")

# Create input messages
messages = [
    {
        "role": "user",
        "content": [
            # {"type": "image"},
            {"type": "image"},
            {"type": "text", 
             "text": """
             Instructions :
             you are visual assistant for blind people, please answer politely and short 
             under 100 words.
             Prompt :
             can you direct me to find toilet
             """}
        ]
    },
]

# Prepare inputs
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
# inputs = processor(text=prompt, return_tensors="pt")
inputs = processor(text=prompt, images=[image2], return_tensors="pt")
inputs = inputs.to(DEVICE)
# Generate outputs
from time import time

tim1 = time()
generated_ids = model.generate(**inputs, max_new_tokens=120)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)
tim2 = time()
print(f"{(tim2 - tim1)} detik")
print(generated_texts[0].split("Assistant: ")[1])