Instructions to use microsoft/Phi-3-mini-4k-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-3-mini-4k-instruct with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Phi-3-mini-4k-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-mini-4k-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-mini-4k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-3-mini-4k-instruct

SGLang

How to use microsoft/Phi-3-mini-4k-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-mini-4k-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-mini-4k-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-mini-4k-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-mini-4k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-3-mini-4k-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-3-mini-4k-instruct
```

KeyError: 'type' when using pipeline with Phi-3-mini-4k-instruct on Kaggle/Colab

#114

by tusherbhomik - opened Feb 18

Discussion

tusherbhomik

Feb 18

I am trying to run the Phi-3-mini-4k-instruct model using the high-level pipeline API, but it fails during initialization with a KeyError: 'type'. This happens within the _init_rope method of the remote modeling code.

Environment:

Platform: Kaggle Notebook (also reproducible in Google Colab)

Library: transformers (latest version installed via pip install -U transformers)

Python: 3.12

Code Snippet Used:


from transformers import pipeline

# Standard snippet from the model card
pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)

messages = [
    {"role": "user", "content": "Who are you?"},
]
print(pipe(messages))

Full Traceback:

KeyError: 'type'
...
~/.cache/huggingface/modules/transformers_modules/microsoft/Phi-3-mini-4k-instruct/.../modeling_phi3.py in _init_rope(self)
    294             )
    295         else:
--> 296             scaling_type = self.config.rope_scaling["type"]
    297             if scaling_type == "longrope":
    298                 self.rotary_emb = Phi3LongRoPEScaledRotaryEmbedding(self.head_dim, self.config)

Observation:
It seems that the config.json or the rope_scaling dictionary for the Phi-3 model is missing the "type" key, or the remote modeling_phi3.py is expecting a schema that doesn't match the current configuration file provided in the repository.

Also, even with attn_implementation='eager', the error persists.

Request:
Could the team please check if the config.json needs an update or if the modeling_phi3.py script needs a fallback for the missing scaling_type?

aywizard

Apr 4

Looks like Phi-3 Mini-4K-Instruct has been integrated in the 4.41.2 version of transformers. https://huggingface.co/microsoft/Phi-3-mini-4k-instruct#how-to-use

The following command works for me.

!pip uninstall -y transformers
!pip install transformers==4.41.2

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