GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
utter-project
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
utter-project
Model Tree
Input Modalities
Output Modalities
Supported Functionality
EuroVLM-9B is a 9B+400M parameter vision-language model that combines the multilingual capabilities of EuroLLM-9B with vision encoding components.
EuroVLM-9B was (visually) instruction tuned on a combination of multilingual vision-language datasets, including image captioning, visual question answering, and multimodal reasoning tasks across the supported languages.
EuroVLM uses a multimodal architecture combining a vision encoder with the EuroLLM language model:
Language Model Component:
Vision Component:
To use the model with HuggingFace's Transformers library
python
from PIL import Imagefrom 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 imageimage = 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))You can also run EuroVLM with vLLM!
python
from vllm import LLM, SamplingParams # Initialize the modelmodel_id = "utter-project/EuroVLM-9B-Preview"llm = LLM(model=model_id) # Set up sampling parameterssampling_params = SamplingParams(temperature=0.7, max_tokens=1024) # Image and promptimage_url = "/url/of/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_url", "image_url": {"url": image_url}}, {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese in one sentence."} ] },] # Generate responseoutputs = llm.chat(messages, sampling_params=sampling_params)print(outputs[0].outputs[0].text)EuroVLM-9B-Instruct supports a wide range of vision-language tasks across multiple languages:
EuroVLM-9B has not been fully aligned to human preferences, so the model may generate problematic outputs in both text and image understanding contexts (e.g., hallucinations about image content, harmful content, biased interpretations, or false statements about visual information).
Additional considerations for multimodal models include:
Users should exercise caution and implement appropriate safety measures when deploying this model in production environments.
from PIL import Imagefrom 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 imageimage = 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))from vllm import LLM, SamplingParams # Initialize the modelmodel_id = "utter-project/EuroVLM-9B-Preview"llm = LLM(model=model_id) # Set up sampling parameterssampling_params = SamplingParams(temperature=0.7, max_tokens=1024) # Image and promptimage_url = "/url/of/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_url", "image_url": {"url": image_url}}, {"type": "text", "text": "What do you see in this image? Please describe it in Portuguese in one sentence."} ] },] # Generate responseoutputs = llm.chat(messages, sampling_params=sampling_params)print(outputs[0].outputs[0].text)