Instructions to use Sigurdur/icebreaker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sigurdur/icebreaker with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Sigurdur/icebreaker")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Sigurdur/icebreaker") model = AutoModelForMultimodalLM.from_pretrained("Sigurdur/icebreaker") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Sigurdur/icebreaker with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sigurdur/icebreaker" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sigurdur/icebreaker", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sigurdur/icebreaker
- SGLang
How to use Sigurdur/icebreaker 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 "Sigurdur/icebreaker" \ --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": "Sigurdur/icebreaker", "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 "Sigurdur/icebreaker" \ --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": "Sigurdur/icebreaker", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Sigurdur/icebreaker with Docker Model Runner:
docker model run hf.co/Sigurdur/icebreaker
metadata
language:
- is
library_name: transformers
datasets:
- Sigurdur/icebreaker-data
Icebreaker
author: Sigurdur Haukur Birgisson
A small pre-trained transformer on some of the data from clarin.is or RMH.
The dataset can be found at http://huggingface.co/Sigurdur/icebreaker-data.
here are some extra characters so that the description card can be longer than 200 characters in length. You don't need to read this, so just close your eyes or look away. Why are you still reading this probably has lots of typos. Seriously, stop reading right now. Ok then, I think this is enough of words.