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

vLLM

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

SGLang

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
```

YenChunChen commited on May 30, 2024

Commit

ff0d44e

1 Parent(s): bfc0c05

update readme regarding FA2

Browse files

Files changed (1) hide show

README.md +1 -19

README.md CHANGED Viewed

@@ -105,7 +105,7 @@ from transformers import AutoProcessor
 model_id = "microsoft/Phi-3-vision-128k-instruct"
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True, torch_dtype="auto")
 processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
@@ -217,24 +217,6 @@ Note that by default, the Phi-3-Vision-128K model uses flash attention, which re
 * NVIDIA A6000
 * NVIDIA H100
-### Running on Windows or without flash attention
-To enable the model on these enviroment here are steps that you may consider to follow:
-Step 1: comment flash attention import code in modeling_phi3_v.py from line 52 to line 56.
-```python
-# if is_flash_attn_2_available():
-#     from flash_attn import flash_attn_func, flash_attn_varlen_func
-#     from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa
-#     _flash_supports_window_size = "window_size" in list(inspect.signature(flash_attn_func).parameters)
-```
-Step 2: change _"_attn_implementation"_ from _"flash_attention_2"_ to _"eager"_ in config.json or disable flash attention when you create the model as below.
-```python
-model = AutoModelForCausalLM.from_pretrained('microsoft/Phi-3-vision-128k-instruct', device_map="cuda", trust_remote_code=True, torch_dtype="auto", _attn_implementation="eager")
-```
 ## License
 The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/resolve/main/LICENSE).

 model_id = "microsoft/Phi-3-vision-128k-instruct"
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True, torch_dtype="auto", attn_implementation='eager') # use attn_implementation='flash_attention_2' to enable flash attention
 processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
 * NVIDIA A6000
 * NVIDIA H100
 ## License
 The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/resolve/main/LICENSE).