Instructions to use IntelLabs/sqft-phi-3-mini-4k-40-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IntelLabs/sqft-phi-3-mini-4k-40-base with Transformers:

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

pipe = pipeline("text-generation", model="IntelLabs/sqft-phi-3-mini-4k-40-base", 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("IntelLabs/sqft-phi-3-mini-4k-40-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("IntelLabs/sqft-phi-3-mini-4k-40-base", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IntelLabs/sqft-phi-3-mini-4k-40-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IntelLabs/sqft-phi-3-mini-4k-40-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IntelLabs/sqft-phi-3-mini-4k-40-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IntelLabs/sqft-phi-3-mini-4k-40-base

SGLang

How to use IntelLabs/sqft-phi-3-mini-4k-40-base 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 "IntelLabs/sqft-phi-3-mini-4k-40-base" \
    --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": "IntelLabs/sqft-phi-3-mini-4k-40-base",
		"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 "IntelLabs/sqft-phi-3-mini-4k-40-base" \
        --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": "IntelLabs/sqft-phi-3-mini-4k-40-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IntelLabs/sqft-phi-3-mini-4k-40-base with Docker Model Runner:
```
docker model run hf.co/IntelLabs/sqft-phi-3-mini-4k-40-base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SQFT Base Model: sqft-phi-3-mini-4k-40-base

Source Model: microsoft/Phi-3-mini-4k-instruct
Sparse Method: Wanda
Sparsity: 40%
Quantization: No

Model Sources

Repository: https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT

Paper:

How to get this model

Refer to the command in SQFT/run_command/phi-3-mini-4k-instruct/sparse_quantization.sh#11.

Citation

@inproceedings{munoz-etal-2024-sqft,
    title = "{SQFT}: Low-cost Model Adaptation in Low-precision Sparse Foundation Models",
    author = "Munoz, Juan Pablo  and
      Yuan, Jinjie  and
      Jain, Nilesh",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.749",
    pages = "12817--12832",
}

Acknowledgement

Thanks to the work Wanda (paper, code), which provides a simple but effective pruning approach.

License

Apache-2.0

Downloads last month: 8

Safetensors

Model size

4B params

Tensor type

F16

Model tree for IntelLabs/sqft-phi-3-mini-4k-40-base

Quantizations

2 models

Collection including IntelLabs/sqft-phi-3-mini-4k-40-base

SQFT

Collection

SQFT Models (SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models) • 57 items • Updated Jun 25, 2025 • 2

Papers for IntelLabs/sqft-phi-3-mini-4k-40-base