Instructions to use Ramavill/twBETO_v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ramavill/twBETO_v0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Ramavill/twBETO_v0")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Ramavill/twBETO_v0") model = AutoModelForMaskedLM.from_pretrained("Ramavill/twBETO_v0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
CUDA error: device-side assert triggered
#1
by erickdp - opened
When I fine tuning your model in Colab with GPU, I get this issue:
- CUDA error: device-side assert triggered
However, my dataset have 3 labels: 1, 0 and 2. And its length is ~5k (include train and test in spanish tweets, post and news).
I didn't have same problem with other models like distilBert, beto base, etc.
Could you give me a hand with that problem? I fine tuning one for text classification.

