Skip to content

phi3v_local_img

Runnable Python SDK example phi3v_local_img.

from mistralrs import Runner, Which, ChatCompletionRequest, MultimodalArchitecture
runner = Runner(
which=Which.MultimodalPlain(
model_id="microsoft/Phi-3.5-vision-instruct",
arch=MultimodalArchitecture.Phi3V,
),
)
FILENAME = "picture.jpg"
res = runner.send_chat_completion_request(
ChatCompletionRequest(
model="default",
messages=[
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": FILENAME,
},
},
{
"type": "text",
"text": "What is shown in this image? Write a detailed response analyzing the scene.",
},
],
}
],
max_tokens=256,
presence_penalty=1.0,
top_p=0.1,
temperature=0.1,
)
)
print(res.choices[0].message.content)
print(res.usage)

Source: examples/python/phi3v_local_img.py