Icebreaker
Collection
3 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Sigurdur/icebreaker")
model = AutoModelForCausalLM.from_pretrained("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.
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Sigurdur/icebreaker")