Sigurdur/icebreaker-data
Preview • Updated • 12
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")How to use Sigurdur/icebreaker with vLLM:
# 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
}'docker model run hf.co/Sigurdur/icebreaker
How to use Sigurdur/icebreaker with SGLang:
# 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
}'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
}'How to use Sigurdur/icebreaker with Docker Model Runner:
docker model run hf.co/Sigurdur/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.