Instructions to use marcderbauer/vice-headlines with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marcderbauer/vice-headlines with Transformers:

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

pipe = pipeline("text-generation", model="marcderbauer/vice-headlines")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("marcderbauer/vice-headlines")
model = AutoModelForCausalLM.from_pretrained("marcderbauer/vice-headlines")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use marcderbauer/vice-headlines with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/marcderbauer/vice-headlines

SGLang

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

Docker Model Runner
How to use marcderbauer/vice-headlines with Docker Model Runner:
```
docker model run hf.co/marcderbauer/vice-headlines
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model generates YouTube titles in the style of VICE.

Here's the GitHub repo associated with it:

Downloads last month: 14

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for marcderbauer/vice-headlines

Quantizations

2 models

marcderbauer
/

vice-headlines

Model tree for marcderbauer/vice-headlines

Space using marcderbauer/vice-headlines 1