Feature Extraction
Transformers
PyTorch
Safetensors
German
modernbert
fill-mask
masked-lm
long-context
text-embeddings-inference
Instructions to use LSX-UniWue/ModernGBERT_134M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LSX-UniWue/ModernGBERT_134M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="LSX-UniWue/ModernGBERT_134M")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("LSX-UniWue/ModernGBERT_134M") model = AutoModelForMaskedLM.from_pretrained("LSX-UniWue/ModernGBERT_134M", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Adjust max length in tokenizer config
#4
by aehrm - opened
Update tokenizer configuration to align max length with config.json. This change does not affect the tokenizer's output. It only prevents (incorrect) warnings for sequences exceeding 1024 tokens.
JanPf changed pull request status to merged