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

Libraries

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

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-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-128k-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True, device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Phi-3-mini-128k-instruct / sample_finetune.py

gugarosa

chore(root): Initial files upload.

780ec16 over 2 years ago

Raw

History Blame

2.37 kB

	import torch
	from datasets import load_dataset
	from trl import SFTTrainer
	from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments

	"""
	Please note that A100 or later generation GPUs are required to finetune Phi-3 models
	1. Install accelerate:
	conda install -c conda-forge accelerate
	2. Setup accelerate config:
	accelerate config
	to simply use all the GPUs available:
	python -c "from accelerate.utils import write_basic_config; write_basic_config(mixed_precision='bf16')"
	check accelerate config:
	accelerate env
	3. Run the code:
	accelerate launch phi3-mini-sample-ft.py
	"""

	###################
	# Hyper-parameters
	###################


	args = {
	"bf16": True,
	"do_eval": False,
	"evaluation_strategy": "no",
	"eval_steps": 100,
	"learning_rate": 5.0e-06,
	"log_level": "info",
	"logging_steps": 20,
	"logging_strategy": "steps",
	"lr_scheduler_type": "cosine",
	"num_train_epochs": 1,
	"max_steps": -1,
	"output_dir": ".",
	"overwrite_output_dir": True,
	"per_device_eval_batch_size": 4,
	"per_device_train_batch_size": 8,
	"remove_unused_columns": True,
	"save_steps": 100,
	"save_total_limit": 1,
	"seed": 0,
	"gradient_checkpointing": True,
	"gradient_accumulation_steps": 1,
	"warmup_ratio": 0.1,
	}

	training_args = TrainingArguments(**args)


	################
	# Modle Loading
	################

	checkpoint_path = "microsoft/Phi-3-mini-128k-instruct"
	model_kwargs = dict(
	trust_remote_code=True,
	attn_implementation="flash_attention_2", # load the model with flash-attenstion support
	torch_dtype=torch.bfloat16,
	device_map="cuda",
	)
	model = AutoModelForCausalLM.from_pretrained(checkpoint_path, **model_kwargs)
	tokenizer = AutoTokenizer.from_pretrained(checkpoint_path, trust_remote_code=True)

	################
	# Data Loading
	################

	dataset = load_dataset("imdb")
	train_dataset = dataset["train"]
	eval_dataset = dataset["test"]


	################
	# Training
	################

	trainer = SFTTrainer(
	model=model,
	args=training_args,
	train_dataset=train_dataset,
	max_seq_length=2048,
	dataset_text_field="text",
	tokenizer=tokenizer,
	)
	train_result = trainer.train()
	metrics = train_result.metrics
	trainer.log_metrics("train", metrics)
	trainer.save_metrics("train", metrics)
	trainer.save_state()