Instructions to use atsumoto/phi-2-alpaca-cleaned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use atsumoto/phi-2-alpaca-cleaned with Transformers:

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

pipe = pipeline("text-generation", model="atsumoto/phi-2-alpaca-cleaned", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("atsumoto/phi-2-alpaca-cleaned", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("atsumoto/phi-2-alpaca-cleaned", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use atsumoto/phi-2-alpaca-cleaned with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/atsumoto/phi-2-alpaca-cleaned

SGLang

How to use atsumoto/phi-2-alpaca-cleaned 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 "atsumoto/phi-2-alpaca-cleaned" \
    --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": "atsumoto/phi-2-alpaca-cleaned",
		"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 "atsumoto/phi-2-alpaca-cleaned" \
        --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": "atsumoto/phi-2-alpaca-cleaned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use atsumoto/phi-2-alpaca-cleaned with Docker Model Runner:
```
docker model run hf.co/atsumoto/phi-2-alpaca-cleaned
```

phi-2-alpaca-cleaned

Commit History

Update README.md

afc4c53
verified

Atsumoto Ohashi commited on Feb 1, 2024

Update README.md

7be8b25
verified

Atsumoto Ohashi commited on Feb 1, 2024

Update README.md

c5a510c
verified

Atsumoto Ohashi commited on Feb 1, 2024

Update README.md

2530f52
verified

Atsumoto Ohashi commited on Feb 1, 2024

Update README.md

0c37728
verified

Atsumoto Ohashi commited on Feb 1, 2024

Create README.md

b75a0bc
verified

Atsumoto Ohashi commited on Feb 1, 2024

Upload tokenizer

2f62ccf
verified

Atsumoto Ohashi commited on Feb 1, 2024

Upload PhiForCausalLM

6954e42
verified

Atsumoto Ohashi commited on Feb 1, 2024

initial commit

48fa382
verified

Atsumoto Ohashi commited on Feb 1, 2024

Commit History

Update README.md afc4c53 verified

Update README.md 7be8b25 verified

Update README.md c5a510c verified

Update README.md 2530f52 verified

Update README.md 0c37728 verified

Create README.md b75a0bc verified

Upload tokenizer 2f62ccf verified

Upload PhiForCausalLM 6954e42 verified

initial commit 48fa382 verified

Update README.md

afc4c53
verified

Update README.md

7be8b25
verified

Update README.md

c5a510c
verified

Update README.md

2530f52
verified

Update README.md

0c37728
verified

Create README.md

b75a0bc
verified

Upload tokenizer

2f62ccf
verified

Upload PhiForCausalLM

6954e42
verified

initial commit

48fa382
verified