Instructions to use Lexius/Phi-3.5-vision-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lexius/Phi-3.5-vision-instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Lexius/Phi-3.5-vision-instruct", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Lexius/Phi-3.5-vision-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Lexius/Phi-3.5-vision-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lexius/Phi-3.5-vision-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lexius/Phi-3.5-vision-instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Lexius/Phi-3.5-vision-instruct

SGLang

How to use Lexius/Phi-3.5-vision-instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Lexius/Phi-3.5-vision-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lexius/Phi-3.5-vision-instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Lexius/Phi-3.5-vision-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lexius/Phi-3.5-vision-instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Lexius/Phi-3.5-vision-instruct with Docker Model Runner:
```
docker model run hf.co/Lexius/Phi-3.5-vision-instruct
```

Again the similar error

by raxtemur - opened Jul 31, 2025

Discussion

raxtemur

Jul 31, 2025

  File "/home/jovyan/.cache/huggingface/modules/transformers_modules/Lexius/Phi-3.5-vision-instruct/88fa59eca4f9b856a9d9ef58b14b32d2d80b0973/modeling_phi3_v.py", line 1417, in forward
    past_key_values_length = past_key_values.get_usable_length(seq_length)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'DynamicCache' object has no attribute 'get_usable_length'. Did you mean: 'get_seq_length'?

  File "/home/jovyan/.cache/huggingface/modules/transformers_modules/Lexius/Phi-3.5-vision-instruct/88fa59eca4f9b856a9d9ef58b14b32d2d80b0973/modeling_phi3_v.py", line 786, in forward
    kv_seq_len += past_key_value.get_usable_length(kv_seq_len, self.layer_idx)

  File "/home/jovyan/.cache/huggingface/modules/transformers_modules/Lexius/Phi-3.5-vision-instruct/88fa59eca4f9b856a9d9ef58b14b32d2d80b0973/modeling_phi3_v.py", line 1660, in prepare_inputs_for_generation
    past_length = past_key_values.seen_tokens
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'DynamicCache' object has no attribute 'seen_tokens'

Lexius

Owner Aug 7, 2025

Sorry for the delay, I somehow didn't get any notification about this issue...

These are different errors. The original error was DynamicCache' object has no attribute 'get_max_length'

The new errors are:

AttributeError: 'DynamicCache' object has no attribute 'get_usable_length'. Did you mean: 'get_seq_length'?
AttributeError: 'DynamicCache' object has no attribute 'seen_tokens'

I'll fix it... thanks for reporting.

MiNeves-tops

Sep 8, 2025

have these new errors like 'seen_tokens' been fixed?

CeloAlvear

Oct 18, 2025

ive been having trubles with the compatibiliti of transformers,
DynamicCache' object has no attribute 'get_max_length'
NameError: name 'use_legacy_cache' is not defined

lerignoux

Oct 27, 2025

Hello

This should be fixed in https://huggingface.co/Lexius/Phi-3.5-vision-instruct/discussions/2

Lexius

Owner Oct 27, 2025

Thanks @lerignoux !

Lexius changed discussion status to closed Oct 27, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment