SakalYin/Qwen2-VL-2B-RobotArm-Camera

from unsloth import FastVisionModel
from PIL import Image
from transformers import TextStreamer
model, processor = FastVisionModel.from_pretrained(
        'SakalYin\Qwen2-VL-2B-RobotArm-Camera',
        load_in_4bit=True,   
        local_files_only=True,
        attn_implementation="flash_attention_2",
    )
def resize_image(image_input, size=None):
    """Load image from path or matrices and resize them"""
    size = size if size else (854,480)
    if isinstance(image_input, str):  
        image = Image.open(image_input)
    else:  
        image = image_input
    size = size if size else (854,480)
    image = image.resize(size).convert('RGB') 
    return image
image_path = "https://i.imgur.com/vAleq1e.png"
size = (854, 480) # Recommeded Size
system_message = "You are a Visual Language Model Trained to output robot arm end-effectors parameters. Base on the user requests, locate the appropriate object in the image and you must return the position and orientation to reach it in xml format."
prompt = "Give me a cup.<camera>0.5,-0.75,1.8</camera>"
image = resize_image(image_path, size=size)
messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": system_message if system_message else "You are a helpful assistant."}],
    },
    {"role": "user", "content": [
        {"type": "image"},
        {"type": "text", "text": prompt}]
    }
]
input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(
    image,
    input_text,
    add_special_tokens=False,
    return_tensors="pt",
).to("cuda")
# Generate text without using the streamer
text_streamer = TextStreamer(processor, skip_prompt=True)
generated_tokens = model.generate(
    **inputs,
    streamer=text_streamer,  
    max_new_tokens=128, 
    use_cache=True, 
    temperature=1.5, 
    min_p=0.1
)
# Decode output properly
output_text = processor.decode(generated_tokens[0], skip_special_tokens=True).strip()