Transformers documentation

Mistral 3

Transformers

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.22.1).

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Bu model, 2025-03-18 tarihinde Hugging Face Transformers'a katkıda bulunulmuştur.

Mistral 3

Mistral 3, ileri geçiş başına süreyi azaltmak için çok daha az katmana sahip, gecikme açısından optimize edilmiş bir modeldir. Bu model, performanstan ödün vermeden 128K token'a kadar uzun bağlam uzunluklarını destekleyen bir görme anlama yeteneği ekler.

Orijinal Mistral 3 kontrol noktalarını Mistral AI kuruluşu altında bulabilirsiniz.

Bu model cyrilvallez ve yonigozlan tarafından katkıda bulunmuştur. Mistral3'ün farklı görevlere nasıl uygulanacağına dair daha fazla örnek için sağ kenar çubuğundaki Mistral3 modellerine tıklayın.

from_pretrained() içinde use_kernels=True değerini ayarlayarak desteklenen katmanları Hub'daki optimize edilmiş çekirdeklerle değiştirin. Daha fazla bilgi için Çekirdekleri yükleme bölümüne bakın.

Aşağıdaki örnek, Pipeline ve AutoModel sınıfı ile bir görüntü için metin üretmenin nasıl yapıldığını göstermektedir.

Pipeline

AutoModel

Notlar

Mistral 3 yalnızca metin üretimi destekler.

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!

/_/\ ( o.o )

^ <

Mistral 3, toplu (batched) görüntü ve metin girdilerini kabul eder.

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://huggingface.co/datasets/hf-internal-testing/transformers-synthetic-assets/resolve/main/images/llava_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"]

Mistral 3, her metin için farklı sayıda görsel içeren toplu görsel ve metin girdilerini de destekliyordu. Aşağıdaki örnek, modeli bitsandbytes ile kuantize eder.

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://huggingface.co/datasets/hf-internal-testing/transformers-synthetic-assets/resolve/main/images/llava_view.jpg"},
                 {"type": "text", "text": "Write a haiku for this image"},
             ],
         },
     ],
     [
         {
             "role": "user",
             "content": [
                 {"type": "image", "url": "https://huggingface.co/datasets/hf-internal-testing/transformers-synthetic-assets/resolve/main/images/statue_of_liberty.jpg"},
                 {"type": "image", "url": "https://huggingface.co/datasets/hf-internal-testing/transformers-synthetic-assets/resolve/main/images/dreamstime_golden_gate_flowers.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."]

Transformers

Mistral 3

Notlar

Mistral3Config

sınıf transformers.Mistral3Config

MistralCommonBackend

sınıf transformers.MistralCommonBackend

add_special_tokens

add_tokens

apply_chat_template

batch_decode

build_inputs_with_special_tokens

convert_added_tokens

create_token_type_ids_from_sequences

decode

encode

from_pretrained

get_chat_template

get_special_tokens_mask

get_vocab

num_special_tokens_to_add

prepare_for_model

save_chat_templates

save_pretrained

save_vocabulary

tokenize

truncate_sequences

Mistral3Model

sınıf transformers.Mistral3Model

forward

get_image_features

get_placeholder_mask

Mistral3ForConditionalGeneration

sınıf transformers.Mistral3ForConditionalGeneration

forward

get_image_features