Instructions to use RichardErkhov/microsoft_-_phi-2-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/microsoft_-_phi-2-4bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/microsoft_-_phi-2-4bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/microsoft_-_phi-2-4bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/microsoft_-_phi-2-4bits")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RichardErkhov/microsoft_-_phi-2-4bits with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RichardErkhov/microsoft_-_phi-2-4bits

SGLang

How to use RichardErkhov/microsoft_-_phi-2-4bits 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 "RichardErkhov/microsoft_-_phi-2-4bits" \
    --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": "RichardErkhov/microsoft_-_phi-2-4bits",
		"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 "RichardErkhov/microsoft_-_phi-2-4bits" \
        --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": "RichardErkhov/microsoft_-_phi-2-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/microsoft_-_phi-2-4bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/microsoft_-_phi-2-4bits
```

RichardErkhov commited on Apr 20, 2024

Commit

ca80cf3

verified ·

1 Parent(s): ec4941b

uploaded model

Browse files

Files changed (1) hide show

model.safetensors +3 -0

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3f347f85eab4b13c389793194caecf1a5740a9bb022d2023959843070ef3ce
+size 1941921136