Instructions to use aleada/Phi-4-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aleada/Phi-4-W4A16 with Transformers:

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

pipe = pipeline("text-generation", model="aleada/Phi-4-W4A16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aleada/Phi-4-W4A16")
model = AutoModelForCausalLM.from_pretrained("aleada/Phi-4-W4A16", 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 aleada/Phi-4-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aleada/Phi-4-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aleada/Phi-4-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aleada/Phi-4-W4A16

SGLang

How to use aleada/Phi-4-W4A16 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 "aleada/Phi-4-W4A16" \
    --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": "aleada/Phi-4-W4A16",
		"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 "aleada/Phi-4-W4A16" \
        --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": "aleada/Phi-4-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aleada/Phi-4-W4A16 with Docker Model Runner:
```
docker model run hf.co/aleada/Phi-4-W4A16
```

Phi-4-W4A16

Commit History

add a link to the pack integrity checker

2742b7c
verified

aleada commited on 13 days ago

model card: record the dampening the run actually used

4331df6
verified

aleada commited on 14 days ago

model card: fix dead links, drop fabricated timing, state Ampere INT4 rationale

27c4e52
verified

aleada commited on 14 days ago

fix(card): substitute repo placeholders + drop vision note for text models

3eb66c7
verified

aleada commited on Jun 30

Add model.safetensors via git-lfs (Xet upload kept hanging)

49b8045

Alex Adamopoulos commited on Jun 30

fix(card): substitute repo placeholders + drop vision note for text models

6e515c7
verified

aleada commited on Jun 30

Add tokenizer_config.json

3b08caa
verified

aleada commited on Jun 30

Add tokenizer.json

ef59c0f
verified

aleada commited on Jun 30

Add recipe.yaml

5e38c84
verified

aleada commited on Jun 30

Add generation_config.json

e77e327
verified

aleada commited on Jun 30

Add config.json

f06ef52
verified

aleada commited on Jun 30

Add chat_template.jinja

d473b93
verified

aleada commited on Jun 30

Add README.md

241193d
verified

aleada commited on Jun 30

initial commit

3d2764a
verified

aleada commited on Jun 30

Commit History

add a link to the pack integrity checker 2742b7c verified

model card: record the dampening the run actually used 4331df6 verified

model card: fix dead links, drop fabricated timing, state Ampere INT4 rationale 27c4e52 verified

fix(card): substitute repo placeholders + drop vision note for text models 3eb66c7 verified

Add model.safetensors via git-lfs (Xet upload kept hanging) 49b8045

fix(card): substitute repo placeholders + drop vision note for text models 6e515c7 verified

Add tokenizer_config.json 3b08caa verified

Add tokenizer.json ef59c0f verified

Add recipe.yaml 5e38c84 verified

Add generation_config.json e77e327 verified

Add config.json f06ef52 verified

Add chat_template.jinja d473b93 verified

Add README.md 241193d verified

initial commit 3d2764a verified

add a link to the pack integrity checker

2742b7c
verified

model card: record the dampening the run actually used

4331df6
verified

model card: fix dead links, drop fabricated timing, state Ampere INT4 rationale

27c4e52
verified

fix(card): substitute repo placeholders + drop vision note for text models

3eb66c7
verified

Add model.safetensors via git-lfs (Xet upload kept hanging)

49b8045

fix(card): substitute repo placeholders + drop vision note for text models

6e515c7
verified

Add tokenizer_config.json

3b08caa
verified

Add tokenizer.json

ef59c0f
verified

Add recipe.yaml

5e38c84
verified

Add generation_config.json

e77e327
verified

Add config.json

f06ef52
verified

Add chat_template.jinja

d473b93
verified

Add README.md

241193d
verified

initial commit

3d2764a
verified