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

Libraries

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

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-small-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-small-128k-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

Move flash_attn assert from init into calling func

#32

by rogerxfeng8 - opened Sep 4, 2024

base: refs/heads/main

←

from: refs/pr/32

Discussion Files changed

-1

rogerxfeng8

Sep 4, 2024

•

edited Sep 5, 2024

When enabling phi-3-small on non-cuda devices, flash_attn package is not available. The assert of flash_attn in init will force the exit. The patch changes the assert into warning, so that we can use customized implementation of flash attention in users' own modeling.

Change the assert to warning in __init__e4f4e18f

Update modeling_phi3_small.pye203eff1

delock

Sep 10, 2024

Hi @nguyenbh , is it possible to review and merge this PR? We found this assertion is blocking non-CUDA device from running this model. If this assertion is removed it won't break CUDA device but will allow non-CUDA device to run this model. Thanks!

bapatra

Microsoft org Sep 10, 2024

Mostly LGTM. One ask: can you move the assert warning into _apply_dense_attn, where (flash_attn_varlen_kvpacked_func is being called ?
Otherwise might be hard to understand that the issue is that flash attention is not available.

rogerxfeng8 changed pull request title from Change the assert to warning in __init__ to Move flash_attn assert from __init__ into calling func Sep 11, 2024

Update modeling_phi3_small.pybef256d0

Moved flash_attn assert close to the callere4770004

rogerxfeng8

Sep 11, 2024

@bapatra hi Barun, thanks for the feedback. PR updated, pls check.

nguyenbh

Microsoft org Sep 12, 2024

Thanks @rogerxfeng8 !

nguyenbh changed pull request status to merged Sep 12, 2024

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