Instructions to use itachi023/phi-2-4-bit-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itachi023/phi-2-4-bit-quantized with Transformers:

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

pipe = pipeline("text-generation", model="itachi023/phi-2-4-bit-quantized")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("itachi023/phi-2-4-bit-quantized")
model = AutoModelForCausalLM.from_pretrained("itachi023/phi-2-4-bit-quantized", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use itachi023/phi-2-4-bit-quantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "itachi023/phi-2-4-bit-quantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itachi023/phi-2-4-bit-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/itachi023/phi-2-4-bit-quantized

SGLang

How to use itachi023/phi-2-4-bit-quantized 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 "itachi023/phi-2-4-bit-quantized" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itachi023/phi-2-4-bit-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "itachi023/phi-2-4-bit-quantized" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itachi023/phi-2-4-bit-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use itachi023/phi-2-4-bit-quantized with Docker Model Runner:
```
docker model run hf.co/itachi023/phi-2-4-bit-quantized
```

itachi023 commited on May 21, 2025

Commit

b62c197

verified ·

1 Parent(s): 83ea5bc

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ This is a 4-bit quantized version of the [microsoft/phi-2](https://huggingface.c
 * **Framework:** 🤗 Transformers
 * **Precision:** 4-bit weights
 * **Quantized size:** \~1.85 GB (original: \~5.5 GB)
-* **Compression ratio:** \~63%
 ---

 * **Framework:** 🤗 Transformers
 * **Precision:** 4-bit weights
 * **Quantized size:** \~1.85 GB (original: \~5.5 GB)
+* **Compression ratio:** \~67%
 ---