Translation
Transformers
PyTorch
Safetensors
t5
text-generation
summarization
text-generation-inference
Instructions to use ybelkada/t5-11b-sharded with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ybelkada/t5-11b-sharded with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="ybelkada/t5-11b-sharded")# Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("ybelkada/t5-11b-sharded") model = AutoModelWithLMHead.from_pretrained("ybelkada/t5-11b-sharded", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- 2.37 kB
- 8.6 kB
- 1.2 kB
- 48.1 kB
- 1.68 GB xet
- 1.68 GB xet
- 1.68 GB xet
- 1.74 GB xet
- 1.74 GB xet
- 1.44 GB xet
- 1.44 GB xet
- 1.28 GB xet
- 1.48 GB xet
- 1.48 GB xet
- 1.31 GB xet
- 1.48 GB xet
- 1.38 GB xet
- 1.38 GB xet
- 1.44 GB xet
- 46.1 kB
- 1.68 GB xet
- 1.68 GB xet
- 1.68 GB xet
- 1.74 GB xet
- 1.74 GB xet
- 1.44 GB xet
- 1.44 GB xet
- 1.28 GB xet
- 1.48 GB xet
- 1.48 GB xet
- 1.31 GB xet
- 1.48 GB xet
- 1.38 GB xet
- 1.38 GB xet
- 1.44 GB xet
- 792 kB xet
- 1.39 MB