Pixtral-12B-2409

pip install --upgrade vllm

pip install --upgrade mistral_common

from vllm import LLM
from vllm.sampling_params import SamplingParams

model_name = "mistralai/Pixtral-12B-2409"

sampling_params = SamplingParams(max_tokens=8192)

llm = LLM(model=model_name, tokenizer_mode="mistral")

prompt = "Describe this image in one sentence."
image_url = "https://picsum.photos/id/237/200/300"

messages = [
    {
        "role": "user",
        "content": [{"type": "text", "text": prompt}, {"type": "image_url", "image_url": {"url": image_url}}]
    },
]

outputs = llm.chat(messages, sampling_params=sampling_params)

print(outputs[0].outputs[0].text)

from vllm import LLM
from vllm.sampling_params import SamplingParams

model_name = "mistralai/Pixtral-12B-2409"
max_img_per_msg = 5

sampling_params = SamplingParams(max_tokens=8192, temperature=0.7)

# Lower max_num_seqs or max_model_len on low-VRAM GPUs.
llm = LLM(model=model_name, tokenizer_mode="mistral", limit_mm_per_prompt={"image": max_img_per_msg}, max_model_len=32768)

prompt = "Describe the following image."

url_1 = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
url_2 = "https://picsum.photos/seed/picsum/200/300"
url_3 = "https://picsum.photos/id/32/512/512"

messages = [
    {
        "role": "user",
        "content": [{"type": "text", "text": prompt}, {"type": "image_url", "image_url": {"url": url_1}}, {"type": "image_url", "image_url": {"url": url_2}}],
    },
    {
        "role": "assistant",
        "content": "The images shows nature.",
    },
    {
        "role": "user",
        "content": "More details please and answer only in French!."
    },
    {
        "role": "user",
        "content": [{"type": "image_url", "image_url": {"url": url_3}}],
    }
]

outputs = llm.chat(messages=messages, sampling_params=sampling_params)
print(outputs[0].outputs[0].text)

vllm serve mistralai/Pixtral-12B-2409 --tokenizer_mode mistral --limit_mm_per_prompt 'image=4'

curl --location 'http://<your-node-url>:8000/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer token' \
--data '{
    "model": "mistralai/Pixtral-12B-2409",
    "messages": [
      {
        "role": "user",
        "content": [
            {"type" : "text", "text": "Describe this image in detail please."},
            {"type": "image_url", "image_url": {"url": "https://s3.amazonaws.com/cms.ipressroom.com/338/files/201808/5b894ee1a138352221103195_A680%7Ejogging-edit/A680%7Ejogging-edit_hero.jpg"}},
            {"type" : "text", "text": "and this one as well. Answer in French."},
            {"type": "image_url", "image_url": {"url": "https://www.wolframcloud.com/obj/resourcesystem/images/a0e/a0ee3983-46c6-4c92-b85d-059044639928/6af8cfb971db031b.png"}}
        ]
      }
    ]
  }'

pip install mistral_inference --upgrade

from huggingface_hub import snapshot_download
from pathlib import Path

mistral_models_path = Path.home().joinpath('mistral_models', 'Pixtral')
mistral_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="mistralai/Pixtral-12B-2409", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)

mistral-chat $HOME/mistral_models/Pixtral --instruct --max_tokens 256 --temperature 0.35

Text prompt: What can you see on the following picture?
[You can input zero, one or more images now.]
Image path or url [Leave empty and press enter to finish image input]: https://picsum.photos/id/237/200/300
Image path or url [Leave empty and press enter to finish image input]:
I see a black dog lying on a wooden surface. The dog appears to be looking up, and its eyes are clearly visible.

from mistral_inference.transformer import Transformer
from mistral_inference.generate import generate

from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.protocol.instruct.messages import UserMessage, TextChunk, ImageURLChunk
from mistral_common.protocol.instruct.request import ChatCompletionRequest

tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json")
model = Transformer.from_folder(mistral_models_path)

url = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
prompt = "Describe the image."

completion_request = ChatCompletionRequest(messages=[UserMessage(content=[ImageURLChunk(image_url=url), TextChunk(text=prompt)])])

encoded = tokenizer.encode_chat_completion(completion_request)

images = encoded.images
tokens = encoded.tokens

out_tokens, _ = generate([tokens], model, images=[images], max_tokens=256, temperature=0.35, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
result = tokenizer.decode(out_tokens[0])

print(result)