</div>

from transformers import pipeline


messages = [
    {"role": "user",
        "content":[
            {"type": "image",
            "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",},
            {"type": "text", "text": "Describe this image."}
        ,]
    ,}
,]

pipeline = pipeline(
    task="image-text-to-text",
    model="mistralai/Mistral-Small-3.1-24B-Instruct-2503",
    device=0
)
outputs = pipeline(text=messages, max_new_tokens=50, return_full_text=False)

outputs[0]["generated_text"]
'The image depicts a vibrant and lush garden scene featuring a variety of wildflowers and plants. The central focus is on a large, pinkish-purple flower, likely a Greater Celandine (Chelidonium majus), with a'

from transformers import AutoModelForImageTextToText, AutoProcessor


model_checkpoint = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
processor = AutoProcessor.from_pretrained(model_checkpoint)
model = AutoModelForImageTextToText.from_pretrained(
    model_checkpoint,
    device_map="auto",
)

messages = [
    {"role": "user",
        "content":[
            {"type": "image",
            "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",},
            {"type": "text", "text": "Describe this image."}
        ,]
    ,}
,]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True, return_dict=True,
    return_tensors="pt").to(model.device)

generate_ids = model.generate(**inputs, max_new_tokens=20)
decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

decoded_output
'The image depicts a vibrant and lush garden scene featuring a variety of wildflowers and plants. The central focus is on a large, pinkish-purple flower, likely a Greater Celandine (Chelidonium majus), with a'

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText

model_checkpoint = ".mistralai/Mistral-Small-3.1-24B-Instruct-2503"
processor = AutoProcessor.from_pretrained(model_checkpoint)
model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map="auto")

SYSTEM_PROMPT = "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat."
user_prompt = "Give me 5 non-formal ways to say 'See you later' in French."

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"role": "user", "content": user_prompt},
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=text, return_tensors="pt").to(0)
generate_ids = model.generate(**inputs, max_new_tokens=50, do_sample=False)
decoded_output = processor.batch_decode(generate_ids[:, inputs["input_ids"].shape[1] :], skip_special_tokens=True)[0]

print(decoded_output)
"1. À plus tard!
 2. Salut, à plus!
 3. À toute!
 4. À la prochaine!
 5. Je me casse, à plus!

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText

model_checkpoint = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
processor = AutoProcessor.from_pretrained(model_checkpoint)
model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map="auto")

messages = [
     [
         {
             "role": "user",
             "content": [
                 {"type": "image", "url": "https://llava-vl.github.io/static/images/view.jpg"},
                 {"type": "text", "text": "Write a haiku for this image"},
             ],
         },
     ],
     [
         {
             "role": "user",
             "content": [
                 {"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"},
                 {"type": "text", "text": "Describe this image"},
             ],
         },
     ],
 ]


 inputs = processor.apply_chat_template(messages, padding=True, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)

 output = model.generate(**inputs, max_new_tokens=25)

 decoded_outputs = processor.batch_decode(output, skip_special_tokens=True)
 decoded_outputs
["Write a haiku for this imageCalm waters reflect\nWhispers of the forest's breath\nPeace on wooden path"
, "Describe this imageThe image depicts a vibrant street scene in what appears to be a Chinatown district. The focal point is a traditional Chinese"]

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText, BitsAndBytesConfig

model_checkpoint = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
processor = AutoProcessor.from_pretrained(model_checkpoint)
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
model = AutoModelForImageTextToText.from_pretrained(
     model_checkpoint, quantization_config=quantization_config
 device_map="auto")

messages = [
     [
         {
             "role": "user",
             "content": [
                 {"type": "image", "url": "https://llava-vl.github.io/static/images/view.jpg"},
                 {"type": "text", "text": "Write a haiku for this image"},
             ],
         },
     ],
     [
         {
             "role": "user",
             "content": [
                 {"type": "image", "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"},
                 {"type": "image", "url": "https://thumbs.dreamstime.com/b/golden-gate-bridge-san-francisco-purple-flowers-california-echium-candicans-36805947.jpg"},
                 {"type": "text", "text": "These images depict two different landmarks. Can you identify them?"},
             ],
         },
     ],
 ]

 inputs = processor.apply_chat_template(messages, padding=True, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)

 output = model.generate(**inputs, max_new_tokens=25)

 decoded_outputs = processor.batch_decode(output, skip_special_tokens=True)
 decoded_outputs
["Write a haiku for this imageSure, here is a haiku inspired by the image:\n\nCalm lake's wooden path\nSilent forest stands guard\n", "These images depict two different landmarks. Can you identify them? Certainly! The images depict two iconic landmarks:\n\n1. The first image shows the Statue of Liberty in New York City."]