Instructions to use yuyijiong/speculative_pipeline_decoding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuyijiong/speculative_pipeline_decoding with Transformers:

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

pipe = pipeline("text-generation", model="yuyijiong/speculative_pipeline_decoding")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("yuyijiong/speculative_pipeline_decoding", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yuyijiong/speculative_pipeline_decoding with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yuyijiong/speculative_pipeline_decoding

SGLang

How to use yuyijiong/speculative_pipeline_decoding 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 "yuyijiong/speculative_pipeline_decoding" \
    --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": "yuyijiong/speculative_pipeline_decoding",
		"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 "yuyijiong/speculative_pipeline_decoding" \
        --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": "yuyijiong/speculative_pipeline_decoding",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yuyijiong/speculative_pipeline_decoding with Docker Model Runner:
```
docker model run hf.co/yuyijiong/speculative_pipeline_decoding
```

Add metadata, paper/code links, and sample usage

by nielsr HF Staff - opened 1 day ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+88

-90

nielsr

1 day ago

Hi! I'm Niels, part of the community science team at Hugging Face.

This PR improves the model card for the Speculative Pipeline Decoding checkpoints by:

Adding YAML metadata (pipeline tag, library name, and license).
Linking the model repository to its respective paper on the Hugging Face Hub.
Adding a link to the official GitHub repository.
Including a sample usage section with a code snippet from the repository to help users run inference.

Please review and merge if this looks good to you!

Add metadata, paper/code links, and sample usage8dea2d08

yuyijiong changed pull request status to merged about 21 hours ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment