EuroVLM-9B-Preview

505
4
9.0B
35 languages
license:apache-2.0
by
utter-project
Image Model
OTHER
9B params
New
505 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
21GB+ RAM
Mobile
Laptop
Server
Quick Summary

⚠️ PREVIEW RELEASE: This is a preview version of EuroVLM-9B.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
9GB+ RAM

Code Examples

Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))
Run the modelpythontransformers
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
    
model_id = "utter-project/EuroVLM-9B-Preview"
processor = LlavaNextProcessor.from_pretrained(model_id)
model = LlavaNextForConditionalGeneration.from_pretrained(model_id)

# Load an image
image = Image.open("/path/to/image.jpg")
    
messages = [
    {
        "role": "system",
        "content": "You are EuroVLM --- a multimodal AI assistant specialized in European languages that provides safe, educational and helpful answers about images and text.",
    },
    {
        "role": "user", 
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese."}
        ]
    },
]

prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(outputs[0], skip_special_tokens=True))

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.