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 "Isaachhe/phi-2_dev" \
--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": "Isaachhe/phi-2_dev",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Copied from https://huggingface.co/susnato/phi-2 commit@9070ddb4fce238899ddbd2aca1faf6a0aeb6e444.
This model can be loaded using HuggingFace transformers commit@4ab5fb8941a38d172b3883c152c34ae2a0b83a68.
Below is the original introduction, which may be expired now.
DISCLAIMER: I don't own the weights to this model, this is a property of Microsoft and taken from their official repository : microsoft/phi-2.
The sole purpose of this repository is to use this model through the transformers API or to load and use the model using the HuggingFace transformers library.
Usage
First make sure you have the latest version of the transformers installed.
pip install -U transformers
Then use the transformers library to load the model from the library itself
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("susnato/phi-2")
tokenizer = AutoTokenizer.from_pretrained("susnato/phi-2")
inputs = tokenizer('''def print_prime(n):
"""
Print all primes between 1 and n
"""''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
- Downloads last month
- 7
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Isaachhe/phi-2_dev" \ --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": "Isaachhe/phi-2_dev", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'