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
Local Apps Settings

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
```

Instruction mode output garbage in text-generation-webui

#14

by raincandy-u - opened Apr 23, 2024

Discussion

raincandy-u

Apr 23, 2024

Prompt tempalte:

{{ '<s>' }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '
' + message['content'] + '<|end|>
' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
' }}{% else %}{{ '<|endoftext|>' }}{% endif %}

Param:

raincandy-u changed discussion status to closed Apr 23, 2024

caiom

Apr 23, 2024

What framework are you using? Have you tried the chat-instruct Mode?

raincandy-u

Apr 23, 2024

Text-generation-webui. I tried and it. Worked, but always added "You:" or "AI:" at the end of output:

raincandy-u changed discussion status to open Apr 23, 2024

raincandy-u

Apr 23, 2024

The chat-instruct prompt:

Continue the chat dialogue below. Write a single reply for the character "<|character|>".

<|prompt|>

The instruction prompt (in the config.json):

{{ '<s>' }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '
' + message['content'] + '<|end|>
' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
' }}{% else %}{{ '<|endoftext|>' }}{% endif %}

theo77186

Apr 23, 2024

It seems text-generation-webui got thrown off by the else in the instruction template. Removing it seems to generate the correct prompt.
The resulting template:

{{ '<s>' }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '
' + message['content'] + '<|end|>
' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
' }}{% endif %}

gugarosa

Microsoft org Apr 23, 2024

You are correct @theo77186 , the current chat_template in the config.json is an attempt to have a template that works for both pre-training and fine-tuning.

When add_generation_prompt is missing, it tries to add an eos_token which finishes the generation and might resolve into unexpected results.

raincandy-u

Apr 24, 2024

Solved!! 😊

raincandy-u changed discussion status to closed Apr 24, 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