microsoft
/

Phi-3-vision-128k-instruct

Text Generation

Model card Files Files and versions

Instructions to use microsoft/Phi-3-vision-128k-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-3-vision-128k-instruct with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-vision-128k-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-vision-128k-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

How to use microsoft/Phi-3-vision-128k-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-3-vision-128k-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": "microsoft/Phi-3-vision-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-3-vision-128k-instruct

How to use microsoft/Phi-3-vision-128k-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 "microsoft/Phi-3-vision-128k-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": "microsoft/Phi-3-vision-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "microsoft/Phi-3-vision-128k-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": "microsoft/Phi-3-vision-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-3-vision-128k-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-3-vision-128k-instruct
```

Phi-3-vision-128k-instruct

Commit History

Update README.md (#73)

ed2772f
verified

bsnelling commited on Dec 10, 2025

Upload data_summary_card.md (#72)

7c760c5
verified

bsnelling commited on Dec 10, 2025

Update README.md

c45209e
verified

nguyenbh commited on Aug 20, 2024

Update README.md

5bc05f2
verified

nguyenbh commited on Aug 20, 2024

Fix generation when `repetition_penalty` is activated (#57)

6065b7a
verified

YenChunChen commited on Aug 5, 2024

Fix number of image tokens (#51)

b161793
verified

mber commited on Jul 30, 2024

Rewrite image embedding to remove the in-place op (#53)

866d169
verified

YenChunChen commited on Jul 17, 2024

Use Flash Attention for CLIP image encoder (#52)

1a87b10
verified

YenChunChen commited on Jul 17, 2024

Update README.md

f998a18
verified

nguyenbh commited on Jul 9, 2024

clean_sample_code (#36)

7b92b8c
verified

haipingwu commited on Jun 11, 2024

Make flash attention configurable in user code (#26)

fea3f11
verified

YenChunChen commited on May 31, 2024

Add link to Phi-3 vision ONNX models

11cb03c
verified

kvaishnavi commited on May 31, 2024

correct the paper reference (#25)

5dcfdfb
verified

leoxiaobin Yixiang Gao commited on May 29, 2024

Update README.md (#14)

dbcdaaa
verified

Criztov commited on May 24, 2024

Update README

2b07137
verified

nguyenbh commited on May 21, 2024

Update README

94f6e2f
verified

nguyenbh commited on May 21, 2024

Update README

034a3df
verified

nguyenbh commited on May 21, 2024

Update README

d33b637
verified

nguyenbh commited on May 21, 2024

Update README

4ed3dc0
verified

nguyenbh commited on May 21, 2024

chore(root): Initial files upload.

44c7c8b

gugarosa commited on May 20, 2024

initial commit

7ba0150
verified

gugarosa commited on May 19, 2024