Instructions to use TOFU-SFT/phi-4-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TOFU-SFT/phi-4-4bit with Transformers:

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

pipe = pipeline("text-generation", model="TOFU-SFT/phi-4-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TOFU-SFT/phi-4-4bit")
model = AutoModelForCausalLM.from_pretrained("TOFU-SFT/phi-4-4bit")
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

vLLM

How to use TOFU-SFT/phi-4-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TOFU-SFT/phi-4-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TOFU-SFT/phi-4-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TOFU-SFT/phi-4-4bit

SGLang

How to use TOFU-SFT/phi-4-4bit 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 "TOFU-SFT/phi-4-4bit" \
    --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": "TOFU-SFT/phi-4-4bit",
		"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 "TOFU-SFT/phi-4-4bit" \
        --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": "TOFU-SFT/phi-4-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TOFU-SFT/phi-4-4bit with Docker Model Runner:
```
docker model run hf.co/TOFU-SFT/phi-4-4bit
```

powidla commited on 23 days ago

Commit

5d9cf0b

verified ·

1 Parent(s): aa8e3c7

Update README.md

Browse files

Files changed (1) hide show

README.md +18 -2

README.md CHANGED Viewed

@@ -21,7 +21,23 @@ widget:
 library_name: transformers
 ---
-# Phi-4 Model Card
-[Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)

 library_name: transformers
 ---
+## Model Description
+- **Developed by**: Microsoft Research
+- **Model type**: Causal Language Models
+- **License**: MIT
+## Bias, Risks, and Limitations
+Warning: This model may produce harmful content
+## Citation
+```
+@article{abdin2024phi,
+  title={Phi-4 technical report},
+  author={Abdin, Marah and Aneja, Jyoti and Behl, Harkirat and Bubeck, S{\'e}bastien and Eldan, Ronen and Gunasekar, Suriya and Harrison, Michael and Hewett, Russell J and Javaheripi, Mojan and Kauffmann, Piero and others},
+  journal={arXiv preprint arXiv:2412.08905},
+  year={2024}
+}