Instructions to use apipack/API-Pack-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apipack/API-Pack-Model with Transformers:

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

pipe = pipeline("text-generation", model="apipack/API-Pack-Model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("apipack/API-Pack-Model")
model = AutoModelForCausalLM.from_pretrained("apipack/API-Pack-Model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use apipack/API-Pack-Model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/apipack/API-Pack-Model

SGLang

How to use apipack/API-Pack-Model 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 "apipack/API-Pack-Model" \
    --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": "apipack/API-Pack-Model",
		"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 "apipack/API-Pack-Model" \
        --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": "apipack/API-Pack-Model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use apipack/API-Pack-Model with Docker Model Runner:
```
docker model run hf.co/apipack/API-Pack-Model
```

API-Pack-Model / README.md

zguo0525

Update README.md

2db0d88 verified over 2 years ago

preview code

Raw History Blame

497 Bytes

metadata

license: apache-2.0
library_name: transformers

This is the repository with model for the paper API Pack A Massive Multi-Programming Language Dataset for API Call Generation.

The model is fine-tuned with 1M instances from API-Pack dataset, and is based on CodeLlama-13b-hf, a custom commercial license for which is available.